2019
Proceedings Articles
Juš Lozej; Dejan Štepec; Vitomir Štruc; Peter Peer
Influence of segmentation on deep iris recognition performance Proceedings Article
V: 7th IAPR/IEEE International Workshop on Biometrics and Forensics (IWBF 2019), 2019.
@inproceedings{lozej2019influence,
title = {Influence of segmentation on deep iris recognition performance},
author = {Juš Lozej and Dejan Štepec and Vitomir Štruc and Peter Peer},
url = {https://arxiv.org/pdf/1901.10431.pdf},
year = {2019},
date = {2019-03-01},
booktitle = {7th IAPR/IEEE International Workshop on Biometrics and Forensics (IWBF 2019)},
journal = {arXiv preprint arXiv:1901.10431},
abstract = {Despite the rise of deep learning in numerous areas of computer vision and image processing, iris recognition has not benefited considerably from these trends so far. Most of the existing research on deep iris recognition is focused on new models for generating discriminative and robust iris representations and relies on methodologies akin to traditional iris recognition pipelines. Hence, the proposed models do not approach iris recognition in an end-to-end manner, but rather use standard heuristic iris segmentation (and unwrapping) techniques to produce normalized inputs for the deep learning models. However, because deep learning is able to model very complex data distributions and nonlinear data changes, an obvious question arises. How important is the use of traditional segmentation methods in a deep learning setting? To answer this question, we present in this paper an empirical analysis of the impact of iris segmentation on the performance of deep learning models using a simple two stage pipeline consisting of a segmentation and a recognition step. We evaluate how the accuracy of segmentation influences recognition performance but also examine if segmentation is needed at all. We use the CASIA Thousand and SBVPI datasets for the experiments and report several interesting findings.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Despite the rise of deep learning in numerous areas of computer vision and image processing, iris recognition has not benefited considerably from these trends so far. Most of the existing research on deep iris recognition is focused on new models for generating discriminative and robust iris representations and relies on methodologies akin to traditional iris recognition pipelines. Hence, the proposed models do not approach iris recognition in an end-to-end manner, but rather use standard heuristic iris segmentation (and unwrapping) techniques to produce normalized inputs for the deep learning models. However, because deep learning is able to model very complex data distributions and nonlinear data changes, an obvious question arises. How important is the use of traditional segmentation methods in a deep learning setting? To answer this question, we present in this paper an empirical analysis of the impact of iris segmentation on the performance of deep learning models using a simple two stage pipeline consisting of a segmentation and a recognition step. We evaluate how the accuracy of segmentation influences recognition performance but also examine if segmentation is needed at all. We use the CASIA Thousand and SBVPI datasets for the experiments and report several interesting findings.
2018
Journal Articles
Klemen Grm; Vitomir Štruc
Deep face recognition for surveillance applications Članek v strokovni reviji
V: IEEE Intelligent Systems, vol. 33, no. 3, str. 46–50, 2018.
@article{GrmIEEE2018,
title = {Deep face recognition for surveillance applications},
author = {Klemen Grm and Vitomir Štruc},
url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2019/08/UniversityOfLjubljana_IEEE_IS_Submission.pdf},
year = {2018},
date = {2018-05-01},
journal = {IEEE Intelligent Systems},
volume = {33},
number = {3},
pages = {46--50},
abstract = {Automated person recognition from surveillance quality footage is an open research problem with many potential application areas. In this paper, we aim at addressing this problem by presenting a face recognition approach tailored towards surveillance applications. The presented approach is based on domain-adapted convolutional neural networks and ranked second in the International Challenge on Biometric Recognition in the Wild (ICB-RW) 2016. We evaluate the performance of the presented approach on part of the Quis-Campi dataset and compare it against several existing face recognition techniques and one (state-of-the-art) commercial system. We find that the domain-adapted convolutional network outperforms all other assessed techniques, but is still inferior to human performance.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Automated person recognition from surveillance quality footage is an open research problem with many potential application areas. In this paper, we aim at addressing this problem by presenting a face recognition approach tailored towards surveillance applications. The presented approach is based on domain-adapted convolutional neural networks and ranked second in the International Challenge on Biometric Recognition in the Wild (ICB-RW) 2016. We evaluate the performance of the presented approach on part of the Quis-Campi dataset and compare it against several existing face recognition techniques and one (state-of-the-art) commercial system. We find that the domain-adapted convolutional network outperforms all other assessed techniques, but is still inferior to human performance.
Žiga Emeršič; Blaž Meden; Peter Peer; Vitomir Štruc
Evaluation and analysis of ear recognition models: performance, complexity and resource requirements Članek v strokovni reviji
V: Neural Computing and Applications, str. 1–16, 2018, ISBN: 0941-0643.
@article{emervsivc2018evaluation,
title = {Evaluation and analysis of ear recognition models: performance, complexity and resource requirements},
author = {Žiga Emeršič and Blaž Meden and Peter Peer and Vitomir Štruc},
url = {https://rdcu.be/Os7a},
doi = {https://doi.org/10.1007/s00521-018-3530-1},
isbn = {0941-0643},
year = {2018},
date = {2018-05-01},
journal = {Neural Computing and Applications},
pages = {1--16},
publisher = {Springer},
abstract = {Ear recognition technology has long been dominated by (local) descriptor-based techniques due to their formidable recognition performance and robustness to various sources of image variability. While deep-learning-based techniques have started to appear in this field only recently, they have already shown potential for further boosting the performance of ear recognition technology and dethroning descriptor-based methods as the current state of the art. However, while recognition performance is often the key factor when selecting recognition models for biometric technology, it is equally important that the behavior of the models is understood and their sensitivity to different covariates is known and well explored. Other factors, such as the train- and test-time complexity or resource requirements, are also paramount and need to be consider when designing recognition systems. To explore these issues, we present in this paper a comprehensive analysis of several descriptor- and deep-learning-based techniques for ear recognition. Our goal is to discover weak points of contemporary techniques, study the characteristics of the existing technology and identify open problems worth exploring in the future. We conduct our analysis through identification experiments on the challenging Annotated Web Ears (AWE) dataset and report our findings. The results of our analysis show that the presence of accessories and high degrees of head movement significantly impacts the identification performance of all types of recognition models, whereas mild degrees of the listed factors and other covariates such as gender and ethnicity impact the identification performance only to a limited extent. From a test-time-complexity point of view, the results suggest that lightweight deep models can be equally fast as descriptor-based methods given appropriate computing hardware, but require significantly more resources during training, where descriptor-based methods have a clear advantage. As an additional contribution, we also introduce a novel dataset of ear images, called AWE Extended (AWEx), which we collected from the web for the training of the deep models used in our experiments. AWEx contains 4104 images of 346 subjects and represents one of the largest and most challenging (publicly available) datasets of unconstrained ear images at the disposal of the research community.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Ear recognition technology has long been dominated by (local) descriptor-based techniques due to their formidable recognition performance and robustness to various sources of image variability. While deep-learning-based techniques have started to appear in this field only recently, they have already shown potential for further boosting the performance of ear recognition technology and dethroning descriptor-based methods as the current state of the art. However, while recognition performance is often the key factor when selecting recognition models for biometric technology, it is equally important that the behavior of the models is understood and their sensitivity to different covariates is known and well explored. Other factors, such as the train- and test-time complexity or resource requirements, are also paramount and need to be consider when designing recognition systems. To explore these issues, we present in this paper a comprehensive analysis of several descriptor- and deep-learning-based techniques for ear recognition. Our goal is to discover weak points of contemporary techniques, study the characteristics of the existing technology and identify open problems worth exploring in the future. We conduct our analysis through identification experiments on the challenging Annotated Web Ears (AWE) dataset and report our findings. The results of our analysis show that the presence of accessories and high degrees of head movement significantly impacts the identification performance of all types of recognition models, whereas mild degrees of the listed factors and other covariates such as gender and ethnicity impact the identification performance only to a limited extent. From a test-time-complexity point of view, the results suggest that lightweight deep models can be equally fast as descriptor-based methods given appropriate computing hardware, but require significantly more resources during training, where descriptor-based methods have a clear advantage. As an additional contribution, we also introduce a novel dataset of ear images, called AWE Extended (AWEx), which we collected from the web for the training of the deep models used in our experiments. AWEx contains 4104 images of 346 subjects and represents one of the largest and most challenging (publicly available) datasets of unconstrained ear images at the disposal of the research community.
Žiga Emeršič; Luka Gabriel; Vitomir Štruc; Peter Peer
Convolutional encoder--decoder networks for pixel-wise ear detection and segmentation Članek v strokovni reviji
V: IET Biometrics, vol. 7, no. 3, str. 175–184, 2018.
@article{emervsivc2018convolutional,
title = {Convolutional encoder--decoder networks for pixel-wise ear detection and segmentation},
author = {Žiga Emeršič and Luka Gabriel and Vitomir Štruc and Peter Peer},
url = {https://arxiv.org/pdf/1702.00307.pdf},
year = {2018},
date = {2018-03-01},
journal = {IET Biometrics},
volume = {7},
number = {3},
pages = {175--184},
publisher = {IET},
abstract = {Object detection and segmentation represents the basis for many tasks in computer and machine vision. In biometric recognition systems the detection of the region-of-interest (ROI) is one of the most crucial steps in the processing pipeline, significantly impacting the performance of the entire recognition system. Existing approaches to ear detection, are commonly susceptible to the presence of severe occlusions, ear accessories or variable illumination conditions and often deteriorate in their performance if applied on ear images captured in unconstrained settings. To address these shortcomings, we present a novel ear detection technique based on convolutional encoder-decoder networks (CEDs). We formulate the problem of ear detection as a two-class segmentation problem and design and train a CED-network architecture to distinguish between image-pixels belonging to the ear and the non-ear class. Unlike competing techniques, our approach does not simply return a bounding box around the detected ear, but provides detailed, pixel-wise information about the location of the ears in the image. Experiments on a dataset gathered from the web (a.k.a. in the wild) show that the proposed technique ensures good detection results in the presence of various covariate factors and significantly outperforms competing methods from the literature.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Object detection and segmentation represents the basis for many tasks in computer and machine vision. In biometric recognition systems the detection of the region-of-interest (ROI) is one of the most crucial steps in the processing pipeline, significantly impacting the performance of the entire recognition system. Existing approaches to ear detection, are commonly susceptible to the presence of severe occlusions, ear accessories or variable illumination conditions and often deteriorate in their performance if applied on ear images captured in unconstrained settings. To address these shortcomings, we present a novel ear detection technique based on convolutional encoder-decoder networks (CEDs). We formulate the problem of ear detection as a two-class segmentation problem and design and train a CED-network architecture to distinguish between image-pixels belonging to the ear and the non-ear class. Unlike competing techniques, our approach does not simply return a bounding box around the detected ear, but provides detailed, pixel-wise information about the location of the ears in the image. Experiments on a dataset gathered from the web (a.k.a. in the wild) show that the proposed technique ensures good detection results in the presence of various covariate factors and significantly outperforms competing methods from the literature.
Blaž Meden; Žiga Emeršič; Vitomir Štruc; Peter Peer
k-Same-Net: k-Anonymity with Generative Deep Neural Networks for Face Deidentification Članek v strokovni reviji
V: Entropy, vol. 20, no. 1, str. 60, 2018.
@article{meden2018k,
title = {k-Same-Net: k-Anonymity with Generative Deep Neural Networks for Face Deidentification},
author = {Blaž Meden and Žiga Emeršič and Vitomir Štruc and Peter Peer},
url = {https://www.mdpi.com/1099-4300/20/1/60/pdf},
year = {2018},
date = {2018-01-01},
journal = {Entropy},
volume = {20},
number = {1},
pages = {60},
publisher = {Multidisciplinary Digital Publishing Institute},
abstract = {Image and video data are today being shared between government entities and other relevant stakeholders on a regular basis and require careful handling of the personal information contained therein. A popular approach to ensure privacy protection in such data is the use of deidentification techniques, which aim at concealing the identity of individuals in the imagery while still preserving certain aspects of the data after deidentification. In this work, we propose a novel approach towards face deidentification, called k-Same-Net, which combines recent Generative Neural Networks (GNNs) with the well-known k-Anonymitymechanism and provides formal guarantees regarding privacy protection on a closed set of identities. Our GNN is able to generate synthetic surrogate face images for deidentification by seamlessly combining features of identities used to train the GNN model. Furthermore, it allows us to control the image-generation process with a small set of appearance-related parameters that can be used to alter specific aspects (e.g., facial expressions, age, gender) of the synthesized surrogate images. We demonstrate the feasibility of k-Same-Net in comprehensive experiments on the XM2VTS and CK+ datasets. We evaluate the efficacy of the proposed approach through reidentification experiments with recent recognition models and compare our results with competing deidentification techniques from the literature. We also present facial expression recognition experiments to demonstrate the utility-preservation capabilities of k-Same-Net. Our experimental results suggest that k-Same-Net is a viable option for facial deidentification that exhibits several desirable characteristics when compared to existing solutions in this area.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Image and video data are today being shared between government entities and other relevant stakeholders on a regular basis and require careful handling of the personal information contained therein. A popular approach to ensure privacy protection in such data is the use of deidentification techniques, which aim at concealing the identity of individuals in the imagery while still preserving certain aspects of the data after deidentification. In this work, we propose a novel approach towards face deidentification, called k-Same-Net, which combines recent Generative Neural Networks (GNNs) with the well-known k-Anonymitymechanism and provides formal guarantees regarding privacy protection on a closed set of identities. Our GNN is able to generate synthetic surrogate face images for deidentification by seamlessly combining features of identities used to train the GNN model. Furthermore, it allows us to control the image-generation process with a small set of appearance-related parameters that can be used to alter specific aspects (e.g., facial expressions, age, gender) of the synthesized surrogate images. We demonstrate the feasibility of k-Same-Net in comprehensive experiments on the XM2VTS and CK+ datasets. We evaluate the efficacy of the proposed approach through reidentification experiments with recent recognition models and compare our results with competing deidentification techniques from the literature. We also present facial expression recognition experiments to demonstrate the utility-preservation capabilities of k-Same-Net. Our experimental results suggest that k-Same-Net is a viable option for facial deidentification that exhibits several desirable characteristics when compared to existing solutions in this area.
Robert Šket; Tadej Debevec; Susanne Kublik; Michael Schloter; Anne Schoeller; Boštjan Murovec; Katarina Vogel Mikuš; Damjan Makuc; Klemen Pečnik; Janez Plavec; Igor B Mekjavić; Ola Eiken; Zala Prevoršek; Blaž Stres
Intestinal Metagenomes and Metabolomes in Healthy Young Males: Inactivity and Hypoxia Generated Negative Physiological Symptoms Precede Microbial Dysbiosis Članek v strokovni reviji
V: Frontiers in Physiology, vol. 9, str. 198, 2018, ISSN: 1664-042X.
@article{10.3389/fphys.2018.00198,
title = {Intestinal Metagenomes and Metabolomes in Healthy Young Males: Inactivity and Hypoxia Generated Negative Physiological Symptoms Precede Microbial Dysbiosis},
author = {Robert Šket and Tadej Debevec and Susanne Kublik and Michael Schloter and Anne Schoeller and Boštjan Murovec and Katarina Vogel Mikuš and Damjan Makuc and Klemen Pečnik and Janez Plavec and Igor B Mekjavić and Ola Eiken and Zala Prevoršek and Blaž Stres},
url = {https://www.frontiersin.org/article/10.3389/fphys.2018.00198},
doi = {10.3389/fphys.2018.00198},
issn = {1664-042X},
year = {2018},
date = {2018-01-01},
urldate = {2018-01-01},
journal = {Frontiers in Physiology},
volume = {9},
pages = {198},
abstract = {We explored the metagenomic, metabolomic and trace metal makeup of intestinal microbiota and environment in healthy male participants during the run-in (5 day) and the following three 21-day interventions: normoxic bedrest (NBR), hypoxic bedrest (HBR) and hypoxic ambulation (HAmb) which were carried out within a controlled laboratory environment (circadian rhythm, fluid and dietary intakes, microbial bioburden, oxygen level, exercise). The fraction of inspired O2 (FiO2) and partial pressure of inspired O2 (PiO2) were 0.209 and 133.1 ± 0.3 mmHg for the NBR and 0.141 ± 0.004 and 90.0 ± 0.4 mmHg (~4000 m simulated altitude) for HBR and HAmb interventions, respectively. Shotgun metagenomes were analyzed at various taxonomic and functional levels, 1H- and 13C -metabolomes were processed using standard quantitative and human expert approaches, whereas metals were assessed using X-ray fluorescence spectrometry. Inactivity and hypoxia resulted in a significant increase in the genus Bacteroides in HBR, in genes coding for proteins involved in iron acquisition and metabolism, cell wall, capsule, virulence, defense and mucin degradation, such as beta-galactosidase (EC3.2.1.23), α-L-fucosidase (EC3.2.1.51), Sialidase (EC3.2.1.18) and α-N-acetylglucosaminidase (EC3.2.1.50). In contrast, the microbial metabolomes, intestinal element and metal profiles, the diversity of bacterial, archaeal and fungal microbial communities were not significantly affected. The observed progressive decrease in defecation frequency and concomitant increase in the electrical conductivity (EC) preceded or took place in absence of significant changes at the taxonomic, functional gene, metabolome and intestinal metal profile levels. The fact that the genus Bacteroides and proteins involved in iron acquisition and metabolism, cell wall, capsule, virulence and mucin degradation were enriched at the end of HBR suggest that both constipation and EC decreased intestinal metal availability leading to modified expression of co-regulated genes in Bacteroides genomes. Bayesian network analysis was used to derive the first hierarchical model of initial inactivity mediated deconditioning steps over time. The PlanHab wash-out period corresponded to a profound life-style change (i.e. reintroduction of exercise) that resulted in stepwise amelioration of the negative physiological symptoms, indicating that exercise apparently prevented the crosstalk between the microbial physiology, mucin degradation and proinflammatory immune activities in the host.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
We explored the metagenomic, metabolomic and trace metal makeup of intestinal microbiota and environment in healthy male participants during the run-in (5 day) and the following three 21-day interventions: normoxic bedrest (NBR), hypoxic bedrest (HBR) and hypoxic ambulation (HAmb) which were carried out within a controlled laboratory environment (circadian rhythm, fluid and dietary intakes, microbial bioburden, oxygen level, exercise). The fraction of inspired O2 (FiO2) and partial pressure of inspired O2 (PiO2) were 0.209 and 133.1 ± 0.3 mmHg for the NBR and 0.141 ± 0.004 and 90.0 ± 0.4 mmHg (~4000 m simulated altitude) for HBR and HAmb interventions, respectively. Shotgun metagenomes were analyzed at various taxonomic and functional levels, 1H- and 13C -metabolomes were processed using standard quantitative and human expert approaches, whereas metals were assessed using X-ray fluorescence spectrometry. Inactivity and hypoxia resulted in a significant increase in the genus Bacteroides in HBR, in genes coding for proteins involved in iron acquisition and metabolism, cell wall, capsule, virulence, defense and mucin degradation, such as beta-galactosidase (EC3.2.1.23), α-L-fucosidase (EC3.2.1.51), Sialidase (EC3.2.1.18) and α-N-acetylglucosaminidase (EC3.2.1.50). In contrast, the microbial metabolomes, intestinal element and metal profiles, the diversity of bacterial, archaeal and fungal microbial communities were not significantly affected. The observed progressive decrease in defecation frequency and concomitant increase in the electrical conductivity (EC) preceded or took place in absence of significant changes at the taxonomic, functional gene, metabolome and intestinal metal profile levels. The fact that the genus Bacteroides and proteins involved in iron acquisition and metabolism, cell wall, capsule, virulence and mucin degradation were enriched at the end of HBR suggest that both constipation and EC decreased intestinal metal availability leading to modified expression of co-regulated genes in Bacteroides genomes. Bayesian network analysis was used to derive the first hierarchical model of initial inactivity mediated deconditioning steps over time. The PlanHab wash-out period corresponded to a profound life-style change (i.e. reintroduction of exercise) that resulted in stepwise amelioration of the negative physiological symptoms, indicating that exercise apparently prevented the crosstalk between the microbial physiology, mucin degradation and proinflammatory immune activities in the host.
Boštjan Murovec; Damjan Makuc; Sabina Kolbl Repinc; Zala Prevoršek; Domen Zavec; Robert Šket; Klemen Pečnik; Janez Plavec; Blaž Stres
1H NMR metabolomics of microbial metabolites in the four MW agricultural biogas plant reactors: A case study of inhibition mirroring the acute rumen acidosis symptoms Članek v strokovni reviji
V: Journal of Environmental Management, vol. 222, str. 428 - 435, 2018, ISSN: 0301-4797.
@article{MUROVEC2018428,
title = {1H NMR metabolomics of microbial metabolites in the four MW agricultural biogas plant reactors: A case study of inhibition mirroring the acute rumen acidosis symptoms},
author = {Boštjan Murovec and Damjan Makuc and Sabina Kolbl Repinc and Zala Prevoršek and Domen Zavec and Robert Šket and Klemen Pečnik and Janez Plavec and Blaž Stres},
url = {http://www.sciencedirect.com/science/article/pii/S0301479718305991},
doi = {https://doi.org/10.1016/j.jenvman.2018.05.068},
issn = {0301-4797},
year = {2018},
date = {2018-01-01},
journal = {Journal of Environmental Management},
volume = {222},
pages = {428 - 435},
abstract = {In this study, nuclear magnetic resonance (1H NMR) spectroscopic profiling was used to provide a more comprehensive view of microbial metabolites associated with poor reactor performance in a full-scale 4 MW mesophilic agricultural biogas plant under fully operational and also under inhibited conditions. Multivariate analyses were used to assess the significance of differences between reactors whereas artificial neural networks (ANN) were used to identify the key metabolites responsible for inhibition and their network of interaction. Based on the results of nm-MDS ordination the subsamples of each reactor were similar, but not identical, despite homogenization of the full-scale reactors before sampling. Hence, a certain extent of variability due to the size of the system under analysis was transferred into metabolome analysis. Multivariate analysis showed that fully active reactors were clustered separately from those containing inhibited reactor metabolites and were significantly different. Furthermore, the three distinct inhibited states were significantly different from each other. The inhibited metabolomes were enriched in acetate, caprylate, trimethylamine, thymine, pyruvate, alanine, xanthine and succinate. The differences in the metabolic fingerprint between inactive and fully active reactors observed in this study resembled closely the metabolites differentiating the (sub) acute rumen acidosis inflicted and healthy rumen metabolomes, creating thus favorable conditions for the growth and activity of pathogenic bacteria. The consistency of our data with those reported before for rumen ecosystems shows that 1H NMR based metabolomics is a reliable approach for the evaluation of metabolic events at full-scale biogas reactors.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In this study, nuclear magnetic resonance (1H NMR) spectroscopic profiling was used to provide a more comprehensive view of microbial metabolites associated with poor reactor performance in a full-scale 4 MW mesophilic agricultural biogas plant under fully operational and also under inhibited conditions. Multivariate analyses were used to assess the significance of differences between reactors whereas artificial neural networks (ANN) were used to identify the key metabolites responsible for inhibition and their network of interaction. Based on the results of nm-MDS ordination the subsamples of each reactor were similar, but not identical, despite homogenization of the full-scale reactors before sampling. Hence, a certain extent of variability due to the size of the system under analysis was transferred into metabolome analysis. Multivariate analysis showed that fully active reactors were clustered separately from those containing inhibited reactor metabolites and were significantly different. Furthermore, the three distinct inhibited states were significantly different from each other. The inhibited metabolomes were enriched in acetate, caprylate, trimethylamine, thymine, pyruvate, alanine, xanthine and succinate. The differences in the metabolic fingerprint between inactive and fully active reactors observed in this study resembled closely the metabolites differentiating the (sub) acute rumen acidosis inflicted and healthy rumen metabolomes, creating thus favorable conditions for the growth and activity of pathogenic bacteria. The consistency of our data with those reported before for rumen ecosystems shows that 1H NMR based metabolomics is a reliable approach for the evaluation of metabolic events at full-scale biogas reactors.
Proceedings Articles
Janez Križaj; Žiga Emeršič; Simon Dobrišek; Peter Peer; Vitomir Štruc
Localization of Facial Landmarks in Depth Images Using Gated Multiple Ridge Descent Proceedings Article
V: 2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI), str. 1–8, IEEE 2018.
@inproceedings{krivzaj2018localization,
title = {Localization of Facial Landmarks in Depth Images Using Gated Multiple Ridge Descent},
author = {Janez Križaj and Žiga Emeršič and Simon Dobrišek and Peter Peer and Vitomir Štruc},
url = {https://ieeexplore.ieee.org/abstract/document/8464215},
year = {2018},
date = {2018-09-01},
booktitle = {2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI)},
pages = {1--8},
organization = {IEEE},
abstract = {A novel method for automatic facial landmark localization is presented. The method builds on the supervised descent framework, which was shown to successfully localize landmarks in the presence of large expression variations and mild occlusions, but struggles when localizing landmarks on faces with large pose variations. We propose an extension of the supervised descent framework that trains multiple descent maps and results in increased robustness to pose variations. The performance of the proposed method is demonstrated on the Bosphorus, the FRGC and the UND data sets for the problem of facial landmark localization from 3D data. Our experimental results show that the proposed method exhibits increased robustness to pose variations, while retaining high performance in the case of expression and occlusion variations.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
A novel method for automatic facial landmark localization is presented. The method builds on the supervised descent framework, which was shown to successfully localize landmarks in the presence of large expression variations and mild occlusions, but struggles when localizing landmarks on faces with large pose variations. We propose an extension of the supervised descent framework that trains multiple descent maps and results in increased robustness to pose variations. The performance of the proposed method is demonstrated on the Bosphorus, the FRGC and the UND data sets for the problem of facial landmark localization from 3D data. Our experimental results show that the proposed method exhibits increased robustness to pose variations, while retaining high performance in the case of expression and occlusion variations.
Matej Kristan; Ales Leonardis; Jiri Matas; Michael Felsberg; Roman Pflugfelder; Luka Cehovin Zajc; Tomas Vojir; Goutam Bhat; Alan Lukezic; Abdelrahman Eldesokey; Vitomir Štruc; Klemen Grm; others
The sixth visual object tracking VOT2018 challenge results Proceedings Article
V: European Conference on Computer Vision Workshops (ECCV-W 2018), 2018.
@inproceedings{kristan2018sixth,
title = {The sixth visual object tracking VOT2018 challenge results},
author = {Matej Kristan and Ales Leonardis and Jiri Matas and Michael Felsberg and Roman Pflugfelder and Luka Cehovin Zajc and Tomas Vojir and Goutam Bhat and Alan Lukezic and Abdelrahman Eldesokey and Vitomir Štruc and Klemen Grm and others},
url = {http://openaccess.thecvf.com/content_ECCVW_2018/papers/11129/Kristan_The_sixth_Visual_Object_Tracking_VOT2018_challenge_results_ECCVW_2018_paper.pdf},
year = {2018},
date = {2018-09-01},
booktitle = {European Conference on Computer Vision Workshops (ECCV-W 2018)},
abstract = {The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking activity organized by the VOT initiative. Results of over eighty trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years. The evaluation included the standard VOT and other popular methodologies for short-term tracking analysis and a “real-time” experiment simulating a situation where a tracker processes images as if provided by a continuously running sensor. A long-term tracking subchallenge has been introduced to the set of standard VOT sub-challenges. The new subchallenge focuses on long-term tracking properties, namely coping with target disappearance and reappearance. A new dataset has been compiled and a performance evaluation methodology that focuses on long-term tracking capabilities has been adopted. The VOT toolkit has been updated to support both standard short-term and the new longterm tracking subchallenges. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The dataset, the evaluation kit and the results are publicly available at the challenge website.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking activity organized by the VOT initiative. Results of over eighty trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years. The evaluation included the standard VOT and other popular methodologies for short-term tracking analysis and a “real-time” experiment simulating a situation where a tracker processes images as if provided by a continuously running sensor. A long-term tracking subchallenge has been introduced to the set of standard VOT sub-challenges. The new subchallenge focuses on long-term tracking properties, namely coping with target disappearance and reappearance. A new dataset has been compiled and a performance evaluation methodology that focuses on long-term tracking capabilities has been adopted. The VOT toolkit has been updated to support both standard short-term and the new longterm tracking subchallenges. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The dataset, the evaluation kit and the results are publicly available at the challenge website.
Peter Rot; Žiga Emeršič; Vitomir Struc; Peter Peer
Deep multi-class eye segmentation for ocular biometrics Proceedings Article
V: 2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI), str. 1–8, IEEE 2018.
@inproceedings{rot2018deep,
title = {Deep multi-class eye segmentation for ocular biometrics},
author = {Peter Rot and Žiga Emeršič and Vitomir Struc and Peter Peer},
url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2019/08/MultiClassReduced.pdf},
year = {2018},
date = {2018-07-01},
booktitle = {2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI)},
pages = {1--8},
organization = {IEEE},
abstract = {Segmentation techniques for ocular biometrics typically focus on finding a single eye region in the input image at the time. Only limited work has been done on multi-class eye segmentation despite a number of obvious advantages. In this paper we address this gap and present a deep multi-class eye segmentation model build around the SegNet architecture. We train the model on a small dataset (of 120 samples) of eye images and observe it to generalize well to unseen images and to ensure highly accurate segmentation results. We evaluate the model on the Multi-Angle Sclera Database (MASD) dataset and describe comprehensive experiments focusing on: i) segmentation performance, ii) error analysis, iii) the sensitivity of the model to changes in view direction, and iv) comparisons with competing single-class techniques. Our results show that the proposed model is viable solution for multi-class eye segmentation suitable for recognition (multi-biometric) pipelines based on ocular characteristics.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Segmentation techniques for ocular biometrics typically focus on finding a single eye region in the input image at the time. Only limited work has been done on multi-class eye segmentation despite a number of obvious advantages. In this paper we address this gap and present a deep multi-class eye segmentation model build around the SegNet architecture. We train the model on a small dataset (of 120 samples) of eye images and observe it to generalize well to unseen images and to ensure highly accurate segmentation results. We evaluate the model on the Multi-Angle Sclera Database (MASD) dataset and describe comprehensive experiments focusing on: i) segmentation performance, ii) error analysis, iii) the sensitivity of the model to changes in view direction, and iv) comparisons with competing single-class techniques. Our results show that the proposed model is viable solution for multi-class eye segmentation suitable for recognition (multi-biometric) pipelines based on ocular characteristics.
Juš Lozej; Blaž Meden; Vitomir Struc; Peter Peer
End-to-end iris segmentation using U-Net Proceedings Article
V: 2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI), str. 1–6, IEEE 2018.
@inproceedings{lozej2018end,
title = {End-to-end iris segmentation using U-Net},
author = {Juš Lozej and Blaž Meden and Vitomir Struc and Peter Peer},
url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2019/08/IWOBI_2018_paper_15.pdf},
year = {2018},
date = {2018-07-01},
booktitle = {2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI)},
pages = {1--6},
organization = {IEEE},
abstract = {Iris segmentation is an important research topic that received significant attention from the research community over the years. Traditional iris segmentation techniques have typically been focused on hand-crafted procedures that, nonetheless, achieved remarkable segmentation performance even with images captured in difficult settings. With the success of deep-learning models, researchers are increasingly looking towards convolutional neural networks (CNNs) to further improve on the accuracy of existing iris segmentation techniques and several CNN-based techniques have already been presented recently in the literature. In this paper we also consider deep-learning models for iris segmentation and present an iris segmentation approach based on the popular U-Net architecture. Our model is trainable end-to-end and, hence, avoids the need for hand designing the segmentation procedure. We evaluate the model on the CASIA dataset and report encouraging results in comparison to existing techniques used in this area.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Iris segmentation is an important research topic that received significant attention from the research community over the years. Traditional iris segmentation techniques have typically been focused on hand-crafted procedures that, nonetheless, achieved remarkable segmentation performance even with images captured in difficult settings. With the success of deep-learning models, researchers are increasingly looking towards convolutional neural networks (CNNs) to further improve on the accuracy of existing iris segmentation techniques and several CNN-based techniques have already been presented recently in the literature. In this paper we also consider deep-learning models for iris segmentation and present an iris segmentation approach based on the popular U-Net architecture. Our model is trainable end-to-end and, hence, avoids the need for hand designing the segmentation procedure. We evaluate the model on the CASIA dataset and report encouraging results in comparison to existing techniques used in this area.
Blaz Meden; Peter Peer; Vitomir Struc
Selective Face Deidentification with End-to-End Perceptual Loss Learning Proceedings Article
V: 2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI), str. 1–7, IEEE 2018.
@inproceedings{meden2018selective,
title = {Selective Face Deidentification with End-to-End Perceptual Loss Learning},
author = {Blaz Meden and Peter Peer and Vitomir Struc},
url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2019/08/Selective_Face_Deidentification_with_End_to_End_Perceptual_Loss_Learning.pdf},
year = {2018},
date = {2018-06-01},
booktitle = {2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI)},
pages = {1--7},
organization = {IEEE},
abstract = {Privacy is a highly debatable topic in the modern technological era. With the advent of massive video and image data (which in a lot of cases contains personal information on the recorded subjects), there is an imminent need for efficient privacy protection mechanisms. To this end, we develop in this work a novel Face Deidentification Network (FaDeNet) that is able to alter the input faces in such a way that automated recognition fail to recognize the subjects in the images, while this is still possible for human observers. FaDeNet is based an encoder-decoder architecture that is trained to auto-encode the input image, while (at the same time) minimizing the recognition performance of a secondary network that is used as an socalled identity critic in FaDeNet. We present experiments on the Radbound Faces Dataset and observe encouraging results.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Privacy is a highly debatable topic in the modern technological era. With the advent of massive video and image data (which in a lot of cases contains personal information on the recorded subjects), there is an imminent need for efficient privacy protection mechanisms. To this end, we develop in this work a novel Face Deidentification Network (FaDeNet) that is able to alter the input faces in such a way that automated recognition fail to recognize the subjects in the images, while this is still possible for human observers. FaDeNet is based an encoder-decoder architecture that is trained to auto-encode the input image, while (at the same time) minimizing the recognition performance of a secondary network that is used as an socalled identity critic in FaDeNet. We present experiments on the Radbound Faces Dataset and observe encouraging results.
Sandipan Banerjee; Joel Brogan; Janez Krizaj; Aparna Bharati; Brandon RichardWebster; Vitomir Struc; Patrick J. Flynn; Walter J. Scheirer
To frontalize or not to frontalize: Do we really need elaborate pre-processing to improve face recognition? Proceedings Article
V: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), str. 20–29, IEEE 2018.
@inproceedings{banerjee2018frontalize,
title = {To frontalize or not to frontalize: Do we really need elaborate pre-processing to improve face recognition?},
author = {Sandipan Banerjee and Joel Brogan and Janez Krizaj and Aparna Bharati and Brandon RichardWebster and Vitomir Struc and Patrick J. Flynn and Walter J. Scheirer},
url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2019/08/To_Frontalize_or_Not_To_Frontalize_Do_We_Really_Ne.pdf},
year = {2018},
date = {2018-05-01},
booktitle = {2018 IEEE Winter Conference on Applications of Computer Vision (WACV)},
pages = {20--29},
organization = {IEEE},
abstract = {Face recognition performance has improved remarkably in the last decade. Much of this success can be attributed to the development of deep learning techniques such as convolutional neural networks (CNNs). While CNNs have pushed the state-of-the-art forward, their training process requires a large amount of clean and correctly labelled training data. If a CNN is intended to tolerate facial pose, then we face an important question: should this training data be diverse in its pose distribution, or should face images be normalized to a single pose in a pre-processing step? To address this question, we evaluate a number of facial landmarking algorithms and a popular frontalization method to understand their effect on facial recognition performance. Additionally, we introduce a new, automatic, single-image frontalization scheme that exceeds the performance of the reference frontalization algorithm for video-to-video face matching on the Point and Shoot Challenge (PaSC) dataset. Additionally, we investigate failure modes of each frontalization method on different facial yaw using the CMU Multi-PIE dataset. We assert that the subsequent recognition and verification performance serves to quantify the effectiveness of each pose correction scheme.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Face recognition performance has improved remarkably in the last decade. Much of this success can be attributed to the development of deep learning techniques such as convolutional neural networks (CNNs). While CNNs have pushed the state-of-the-art forward, their training process requires a large amount of clean and correctly labelled training data. If a CNN is intended to tolerate facial pose, then we face an important question: should this training data be diverse in its pose distribution, or should face images be normalized to a single pose in a pre-processing step? To address this question, we evaluate a number of facial landmarking algorithms and a popular frontalization method to understand their effect on facial recognition performance. Additionally, we introduce a new, automatic, single-image frontalization scheme that exceeds the performance of the reference frontalization algorithm for video-to-video face matching on the Point and Shoot Challenge (PaSC) dataset. Additionally, we investigate failure modes of each frontalization method on different facial yaw using the CMU Multi-PIE dataset. We assert that the subsequent recognition and verification performance serves to quantify the effectiveness of each pose correction scheme.
Žiga Emeršič; Nil Oleart Playa; Vitomir Štruc; Peter Peer
Towards Accessories-Aware Ear Recognition Proceedings Article
V: 2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI), str. 1–8, IEEE 2018.
@inproceedings{emervsivc2018towards,
title = {Towards Accessories-Aware Ear Recognition},
author = {Žiga Emeršič and Nil Oleart Playa and Vitomir Štruc and Peter Peer},
url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2019/08/iwobi-2018-inpaint-1.pdf},
doi = {10.1109/IWOBI.2018.8464138},
year = {2018},
date = {2018-03-01},
booktitle = {2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI)},
pages = {1--8},
organization = {IEEE},
abstract = {Automatic ear recognition is gaining popularity within the research community due to numerous desirable properties, such as high recognition performance, the possibility of capturing ear images at a distance and in a covert manner, etc. Despite this popularity and the corresponding research effort that is being directed towards ear recognition technology, open problems still remain. One of the most important issues stopping ear recognition systems from being widely available are ear occlusions and accessories. Ear accessories not only mask biometric features and by this reduce the overall recognition performance, but also introduce new non-biometric features that can be exploited for spoofing purposes. Ignoring ear accessories during recognition can, therefore, present a security threat to ear recognition and also adversely affect performance. Despite the importance of this topic there has been, to the best of our knowledge, no ear recognition studies that would address these problems. In this work we try to close this gap and study the impact of ear accessories on the recognition performance of several state-of-the-art ear recognition techniques. We consider ear accessories as a tool for spoofing attacks and show that CNN-based recognition approaches are more susceptible to spoofing attacks than traditional descriptor-based approaches. Furthermore, we demonstrate that using inpainting techniques or average coloring can mitigate the problems caused by ear accessories and slightly outperforms (standard) black color to mask ear accessories.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Automatic ear recognition is gaining popularity within the research community due to numerous desirable properties, such as high recognition performance, the possibility of capturing ear images at a distance and in a covert manner, etc. Despite this popularity and the corresponding research effort that is being directed towards ear recognition technology, open problems still remain. One of the most important issues stopping ear recognition systems from being widely available are ear occlusions and accessories. Ear accessories not only mask biometric features and by this reduce the overall recognition performance, but also introduce new non-biometric features that can be exploited for spoofing purposes. Ignoring ear accessories during recognition can, therefore, present a security threat to ear recognition and also adversely affect performance. Despite the importance of this topic there has been, to the best of our knowledge, no ear recognition studies that would address these problems. In this work we try to close this gap and study the impact of ear accessories on the recognition performance of several state-of-the-art ear recognition techniques. We consider ear accessories as a tool for spoofing attacks and show that CNN-based recognition approaches are more susceptible to spoofing attacks than traditional descriptor-based approaches. Furthermore, we demonstrate that using inpainting techniques or average coloring can mitigate the problems caused by ear accessories and slightly outperforms (standard) black color to mask ear accessories.
Rosaura G. Vidal; Sreya Banerjee; Klemen Grm; Vitomir Struc; Walter J. Scheirer
UG^ 2: A Video Benchmark for Assessing the Impact of Image Restoration and Enhancement on Automatic Visual Recognition Proceedings Article
V: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), str. 1597–1606, IEEE 2018.
@inproceedings{vidal2018ug,
title = {UG^ 2: A Video Benchmark for Assessing the Impact of Image Restoration and Enhancement on Automatic Visual Recognition},
author = {Rosaura G. Vidal and Sreya Banerjee and Klemen Grm and Vitomir Struc and Walter J. Scheirer},
url = {https://arxiv.org/pdf/1710.02909.pdf},
year = {2018},
date = {2018-02-01},
booktitle = {2018 IEEE Winter Conference on Applications of Computer Vision (WACV)},
pages = {1597--1606},
organization = {IEEE},
abstract = {Advances in image restoration and enhancement techniques have led to discussion about how such algorithms can be applied as a pre-processing step to improve automatic visual recognition. In principle, techniques like deblurring and super-resolution should yield improvements by de-emphasizing noise and increasing signal in an input image. But the historically divergent goals of computational photography and visual recognition communities have created a significant need for more work in this direction. To facilitate new research, we introduce a new benchmark dataset called UG2, which contains three difficult real-world scenarios: uncontrolled videos taken by UAVs and manned gliders, as well as controlled videos taken on the ground. Over 150,000 annotated frames for hundreds of ImageNet classes are available, which are used for baseline experiments that assess the impact of known and unknown image artifacts and other conditions on common deep learning-based object classification approaches. Further, current image restoration and enhancement techniques are evaluated by determining whether or not they improve baseline classification performance. Results show that there is plenty of room for algorithmic innovation, making this dataset a useful tool going forward.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Advances in image restoration and enhancement techniques have led to discussion about how such algorithms can be applied as a pre-processing step to improve automatic visual recognition. In principle, techniques like deblurring and super-resolution should yield improvements by de-emphasizing noise and increasing signal in an input image. But the historically divergent goals of computational photography and visual recognition communities have created a significant need for more work in this direction. To facilitate new research, we introduce a new benchmark dataset called UG2, which contains three difficult real-world scenarios: uncontrolled videos taken by UAVs and manned gliders, as well as controlled videos taken on the ground. Over 150,000 annotated frames for hundreds of ImageNet classes are available, which are used for baseline experiments that assess the impact of known and unknown image artifacts and other conditions on common deep learning-based object classification approaches. Further, current image restoration and enhancement techniques are evaluated by determining whether or not they improve baseline classification performance. Results show that there is plenty of room for algorithmic innovation, making this dataset a useful tool going forward.
Abhijit Das; Umapada Pal; Miguel A. Ferrer; Michael Blumenstein; Dejan Štepec; Peter Rot; Žiga Emeršič; Peter Peer; Vitomir Štruc
SSBC 2018: Sclera Segmentation Benchmarking Competition Proceedings Article
V: 2018 International Conference on Biometrics (ICB), 2018.
@inproceedings{Dasicb2018,
title = {SSBC 2018: Sclera Segmentation Benchmarking Competition},
author = {Abhijit Das and Umapada Pal and Miguel A. Ferrer and Michael Blumenstein and Dejan Štepec and Peter Rot and Žiga Emeršič and Peter Peer and Vitomir Štruc},
url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2019/08/icb2018_sserbc.pdf},
year = {2018},
date = {2018-02-01},
booktitle = {2018 International Conference on Biometrics (ICB)},
abstract = {This paper summarises the results of the Sclera Segmentation Benchmarking Competition (SSBC 2018). It was organised in the context of the 11th IAPR International Conference on Biometrics (ICB 2018). The aim of this competition was to record the developments on sclera segmentation in the cross-sensor environment (sclera trait captured using multiple acquiring sensors). Additionally, the competition also aimed to gain the attention of researchers on this subject of research. For the purpose of benchmarking, we have developed two datasets of sclera images captured using different sensors. The first dataset was collected using a DSLR camera and the second one was collected using a mobile phone camera. The first dataset is the Multi-Angle Sclera Dataset (MASD version 1), which was used in the context of the previous versions of sclera segmentation competitions. The images in the second dataset were captured using .a mobile phone rear camera of 8-megapixel. As baseline manual segmentation mask of the sclera images from both the datasets were developed. Precision and recall-based statistical measures were employed to evaluate the effectiveness of the submitted segmentation technique and to rank them. Six algorithms were submitted towards the segmentation task. This paper analyses the results produced by these algorithms/system and defines a way forward for this subject of research. Both the datasets along with some of the accompanying ground truth/baseline mask will be freely available for research purposes upon request to authors by email.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper summarises the results of the Sclera Segmentation Benchmarking Competition (SSBC 2018). It was organised in the context of the 11th IAPR International Conference on Biometrics (ICB 2018). The aim of this competition was to record the developments on sclera segmentation in the cross-sensor environment (sclera trait captured using multiple acquiring sensors). Additionally, the competition also aimed to gain the attention of researchers on this subject of research. For the purpose of benchmarking, we have developed two datasets of sclera images captured using different sensors. The first dataset was collected using a DSLR camera and the second one was collected using a mobile phone camera. The first dataset is the Multi-Angle Sclera Dataset (MASD version 1), which was used in the context of the previous versions of sclera segmentation competitions. The images in the second dataset were captured using .a mobile phone rear camera of 8-megapixel. As baseline manual segmentation mask of the sclera images from both the datasets were developed. Precision and recall-based statistical measures were employed to evaluate the effectiveness of the submitted segmentation technique and to rank them. Six algorithms were submitted towards the segmentation task. This paper analyses the results produced by these algorithms/system and defines a way forward for this subject of research. Both the datasets along with some of the accompanying ground truth/baseline mask will be freely available for research purposes upon request to authors by email.
2017
Journal Articles
Žiga Emeršič; Vitomir Štruc; Peter Peer
Ear recognition: More than a survey Članek v strokovni reviji
V: Neurocomputing, vol. 255, str. 26–39, 2017.
@article{emervsivc2017ear,
title = {Ear recognition: More than a survey},
author = {Žiga Emeršič and Vitomir Štruc and Peter Peer},
url = {https://arxiv.org/pdf/1611.06203.pdf},
year = {2017},
date = {2017-01-01},
journal = {Neurocomputing},
volume = {255},
pages = {26--39},
publisher = {Elsevier},
abstract = {Automatic identity recognition from ear images represents an active field of research within the biometric community. The ability to capture ear images from a distance and in a covert manner makes the technology an appealing choice for surveillance and security applications as well as other application domains. Significant contributions have been made in the field over recent years, but open research problems still remain and hinder a wider (commercial) deployment of the technology. This paper presents an overview of the field of automatic ear recognition (from 2D images) and focuses specifically on the most recent, descriptor-based methods proposed in this area. Open challenges are discussed and potential research directions are outlined with the goal of providing the reader with a point of reference for issues worth examining in the future. In addition to a comprehensive review on ear recognition technology, the paper also introduces a new, fully unconstrained dataset of ear images gathered from the web and a toolbox implementing several state-of-the-art techniques for ear recognition. The dataset and toolbox are meant to address some of the open issues in the field and are made publicly available to the research community.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Automatic identity recognition from ear images represents an active field of research within the biometric community. The ability to capture ear images from a distance and in a covert manner makes the technology an appealing choice for surveillance and security applications as well as other application domains. Significant contributions have been made in the field over recent years, but open research problems still remain and hinder a wider (commercial) deployment of the technology. This paper presents an overview of the field of automatic ear recognition (from 2D images) and focuses specifically on the most recent, descriptor-based methods proposed in this area. Open challenges are discussed and potential research directions are outlined with the goal of providing the reader with a point of reference for issues worth examining in the future. In addition to a comprehensive review on ear recognition technology, the paper also introduces a new, fully unconstrained dataset of ear images gathered from the web and a toolbox implementing several state-of-the-art techniques for ear recognition. The dataset and toolbox are meant to address some of the open issues in the field and are made publicly available to the research community.
Blaž Meden; Refik Can Malli; Sebastjan Fabijan; Hazim Kemal Ekenel; Vitomir Štruc; Peter Peer
Face deidentification with generative deep neural networks Članek v strokovni reviji
V: IET Signal Processing, vol. 11, no. 9, str. 1046–1054, 2017.
@article{meden2017face,
title = {Face deidentification with generative deep neural networks},
author = {Blaž Meden and Refik Can Malli and Sebastjan Fabijan and Hazim Kemal Ekenel and Vitomir Štruc and Peter Peer},
url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2019/08/Face_Deidentification_with_Generative_Deep_Neural_Networks.pdf},
year = {2017},
date = {2017-01-01},
journal = {IET Signal Processing},
volume = {11},
number = {9},
pages = {1046--1054},
publisher = {IET},
abstract = {Face deidentification is an active topic amongst privacy and security researchers. Early deidentification methods relying on image blurring or pixelisation have been replaced in recent years with techniques based on formal anonymity models that provide privacy guaranties and retain certain characteristics of the data even after deidentification. The latter aspect is important, as it allows the deidentified data to be used in applications for which identity information is irrelevant. In this work, the authors present a novel face deidentification pipeline, which ensures anonymity by synthesising artificial surrogate faces using generative neural networks (GNNs). The generated faces are used to deidentify subjects in images or videos, while preserving non-identity-related aspects of the data and consequently enabling data utilisation. Since generative networks are highly adaptive and can utilise diverse parameters (pertaining to the appearance of the generated output in terms of facial expressions, gender, race etc.), they represent a natural choice for the problem of face deidentification. To demonstrate the feasibility of the authors’ approach, they perform experiments using automated recognition tools and human annotators. Their results show that the recognition performance on deidentified images is close to chance, suggesting that the deidentification process based on GNNs is effective.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Face deidentification is an active topic amongst privacy and security researchers. Early deidentification methods relying on image blurring or pixelisation have been replaced in recent years with techniques based on formal anonymity models that provide privacy guaranties and retain certain characteristics of the data even after deidentification. The latter aspect is important, as it allows the deidentified data to be used in applications for which identity information is irrelevant. In this work, the authors present a novel face deidentification pipeline, which ensures anonymity by synthesising artificial surrogate faces using generative neural networks (GNNs). The generated faces are used to deidentify subjects in images or videos, while preserving non-identity-related aspects of the data and consequently enabling data utilisation. Since generative networks are highly adaptive and can utilise diverse parameters (pertaining to the appearance of the generated output in terms of facial expressions, gender, race etc.), they represent a natural choice for the problem of face deidentification. To demonstrate the feasibility of the authors’ approach, they perform experiments using automated recognition tools and human annotators. Their results show that the recognition performance on deidentified images is close to chance, suggesting that the deidentification process based on GNNs is effective.
Klemen Grm; Vitomir Štruc; Anais Artiges; Matthieu Caron; Hazim K. Ekenel
Strengths and weaknesses of deep learning models for face recognition against image degradations Članek v strokovni reviji
V: IET Biometrics, vol. 7, no. 1, str. 81–89, 2017.
@article{grm2017strengths,
title = {Strengths and weaknesses of deep learning models for face recognition against image degradations},
author = {Klemen Grm and Vitomir Štruc and Anais Artiges and Matthieu Caron and Hazim K. Ekenel},
url = {https://arxiv.org/pdf/1710.01494.pdf},
year = {2017},
date = {2017-01-01},
journal = {IET Biometrics},
volume = {7},
number = {1},
pages = {81--89},
publisher = {IET},
abstract = {Convolutional neural network (CNN) based approaches are the state of the art in various computer vision tasks including face recognition. Considerable research effort is currently being directed toward further improving CNNs by focusing on model architectures and training techniques. However, studies systematically exploring the strengths and weaknesses of existing deep models for face recognition are still relatively scarce. In this paper, we try to fill this gap and study the effects of different covariates on the verification performance of four recent CNN models using the Labelled Faces in the Wild dataset. Specifically, we investigate the influence of covariates related to image quality and model characteristics, and analyse their impact on the face verification performance of different deep CNN models. Based on comprehensive and rigorous experimentation, we identify the strengths and weaknesses of the deep learning models, and present key areas for potential future research. Our results indicate that high levels of noise, blur, missing pixels, and brightness have a detrimental effect on the verification performance of all models, whereas the impact of contrast changes and compression artefacts is limited. We find that the descriptor-computation strategy and colour information does not have a significant influence on performance.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Convolutional neural network (CNN) based approaches are the state of the art in various computer vision tasks including face recognition. Considerable research effort is currently being directed toward further improving CNNs by focusing on model architectures and training techniques. However, studies systematically exploring the strengths and weaknesses of existing deep models for face recognition are still relatively scarce. In this paper, we try to fill this gap and study the effects of different covariates on the verification performance of four recent CNN models using the Labelled Faces in the Wild dataset. Specifically, we investigate the influence of covariates related to image quality and model characteristics, and analyse their impact on the face verification performance of different deep CNN models. Based on comprehensive and rigorous experimentation, we identify the strengths and weaknesses of the deep learning models, and present key areas for potential future research. Our results indicate that high levels of noise, blur, missing pixels, and brightness have a detrimental effect on the verification performance of all models, whereas the impact of contrast changes and compression artefacts is limited. We find that the descriptor-computation strategy and colour information does not have a significant influence on performance.
Robert Šket; Nicole Treichel; Susanne Kublik; Tadej Debevec; Ola Eiken; Igor Mekjavić; Michael Schloter; Marius Vital; Jenna Chandler; James M Tiedje; Boštjan Murovec; Zala Prevoršek; Matevž Likar; Blaž Stres
Hypoxia and inactivity related physiological changes precede or take place in absence of significant rearrangements in bacterial community structure: The PlanHab randomized trial pilot study Članek v strokovni reviji
V: PLOS ONE, vol. 12, no. 12, str. 1-26, 2017.
@article{10.1371/journal.pone.0188556,
title = {Hypoxia and inactivity related physiological changes precede or take place in absence of significant rearrangements in bacterial community structure: The PlanHab randomized trial pilot study},
author = {Robert Šket and Nicole Treichel and Susanne Kublik and Tadej Debevec and Ola Eiken and Igor Mekjavić and Michael Schloter and Marius Vital and Jenna Chandler and James M Tiedje and Boštjan Murovec and Zala Prevoršek and Matevž Likar and Blaž Stres},
url = {https://doi.org/10.1371/journal.pone.0188556},
doi = {10.1371/journal.pone.0188556},
year = {2017},
date = {2017-01-01},
journal = {PLOS ONE},
volume = {12},
number = {12},
pages = {1-26},
publisher = {Public Library of Science},
abstract = {We explored the assembly of intestinal microbiota in healthy male participants during the randomized crossover design of run-in (5 day) and experimental phases (21-day normoxic bed rest (NBR), hypoxic bed rest (HBR) and hypoxic ambulation (HAmb) in a strictly controlled laboratory environment, with balanced fluid and dietary intakes, controlled circadian rhythm, microbial ambiental burden and 24/7 medical surveillance. The fraction of inspired O2 (FiO2) and partial pressure of inspired O2 (PiO2) were 0.209 and 133.1 ± 0.3 mmHg for NBR and 0.141 ± 0.004 and 90.0 ± 0.4 mmHg for both hypoxic variants (HBR and HAmb; ~4000 m simulated altitude), respectively. A number of parameters linked to intestinal environment such as defecation frequency, intestinal electrical conductivity (IEC), sterol and polyphenol content and diversity, indole, aromaticity and spectral characteristics of dissolved organic matter (DOM) were measured (64 variables). The structure and diversity of bacterial microbial community was assessed using 16S rRNA amplicon sequencing. Inactivity negatively affected frequency of defecation and in combination with hypoxia increased IEC (p < 0.05). In contrast, sterol and polyphenol diversity and content, various characteristics of DOM and aromatic compounds, the structure and diversity of bacterial microbial community were not significantly affected over time. A new in-house PlanHab database was established to integrate all measured variables on host physiology, diet, experiment, immune and metabolic markers (n = 231). The observed progressive decrease in defecation frequency and concomitant increase in IEC suggested that the transition from healthy physiological state towards the developed symptoms of low magnitude obesity-related syndromes was dose dependent on the extent of time spent in inactivity and preceded or took place in absence of significant rearrangements in bacterial microbial community. Species B. thetaiotamicron, B. fragilis, B. dorei and other Bacteroides with reported relevance for dysbiotic medical conditions were significantly enriched in HBR, characterized with most severe inflammation symptoms, indicating a shift towards host mucin degradation and proinflammatory immune crosstalk.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
We explored the assembly of intestinal microbiota in healthy male participants during the randomized crossover design of run-in (5 day) and experimental phases (21-day normoxic bed rest (NBR), hypoxic bed rest (HBR) and hypoxic ambulation (HAmb) in a strictly controlled laboratory environment, with balanced fluid and dietary intakes, controlled circadian rhythm, microbial ambiental burden and 24/7 medical surveillance. The fraction of inspired O2 (FiO2) and partial pressure of inspired O2 (PiO2) were 0.209 and 133.1 ± 0.3 mmHg for NBR and 0.141 ± 0.004 and 90.0 ± 0.4 mmHg for both hypoxic variants (HBR and HAmb; ~4000 m simulated altitude), respectively. A number of parameters linked to intestinal environment such as defecation frequency, intestinal electrical conductivity (IEC), sterol and polyphenol content and diversity, indole, aromaticity and spectral characteristics of dissolved organic matter (DOM) were measured (64 variables). The structure and diversity of bacterial microbial community was assessed using 16S rRNA amplicon sequencing. Inactivity negatively affected frequency of defecation and in combination with hypoxia increased IEC (p < 0.05). In contrast, sterol and polyphenol diversity and content, various characteristics of DOM and aromatic compounds, the structure and diversity of bacterial microbial community were not significantly affected over time. A new in-house PlanHab database was established to integrate all measured variables on host physiology, diet, experiment, immune and metabolic markers (n = 231). The observed progressive decrease in defecation frequency and concomitant increase in IEC suggested that the transition from healthy physiological state towards the developed symptoms of low magnitude obesity-related syndromes was dose dependent on the extent of time spent in inactivity and preceded or took place in absence of significant rearrangements in bacterial microbial community. Species B. thetaiotamicron, B. fragilis, B. dorei and other Bacteroides with reported relevance for dysbiotic medical conditions were significantly enriched in HBR, characterized with most severe inflammation symptoms, indicating a shift towards host mucin degradation and proinflammatory immune crosstalk.
Robert Šket; Nicole Treichel; Tadej Debevec; Ola Eiken; Igor Mekjavic; Michael Schloter; Marius Vital; Jenna Chandler; James M Tiedje; Boštjan Murovec; Zala Prevoršek; Blaž Stres
Hypoxia and Inactivity Related Physiological Changes (Constipation, Inflammation) Are Not Reflected at the Level of Gut Metabolites and Butyrate Producing Microbial Community: The PlanHab Study Članek v strokovni reviji
V: Frontiers in Physiology, vol. 8, str. 250, 2017, ISSN: 1664-042X.
@article{10.3389/fphys.2017.00250,
title = {Hypoxia and Inactivity Related Physiological Changes (Constipation, Inflammation) Are Not Reflected at the Level of Gut Metabolites and Butyrate Producing Microbial Community: The PlanHab Study},
author = {Robert Šket and Nicole Treichel and Tadej Debevec and Ola Eiken and Igor Mekjavic and Michael Schloter and Marius Vital and Jenna Chandler and James M Tiedje and Boštjan Murovec and Zala Prevoršek and Blaž Stres},
url = {https://www.frontiersin.org/article/10.3389/fphys.2017.00250},
doi = {10.3389/fphys.2017.00250},
issn = {1664-042X},
year = {2017},
date = {2017-01-01},
journal = {Frontiers in Physiology},
volume = {8},
pages = {250},
abstract = {We explored the assembly of intestinal microbiota in healthy male participants during the run-in (5 day) and experimental phases (21-day normoxic bed rest (NBR), hypoxic bedrest (HBR) and hypoxic ambulation (HAmb) in a strictly controlled laboratory environment, balanced fluid and dietary intakes, controlled circadian rhythm, microbial ambiental burden and 24/7 medical surveillance. The fraction of inspired O2 (FiO2) and partial pressure of inspired O2 (PiO2) were 0.209 and 133.1 ± 0.3 mmHg for NBR and 0.141 ± 0.004 and 90.0 ± 0.4 mmHg for both hypoxic variants (HBR and HAmb; ~4000 m simulated altitude), respectively. A number of parameters linked to intestinal transit spanning Bristol Stool Scale, defecation rates, zonulin, α1-antitrypsin, eosinophil derived neurotoxin, bile acids, reducing sugars, short chain fatty acids, total soluble organic carbon, water content, diet composition and food intake were measured (167 variables). The abundance, structure and diversity of butyrate producing microbial community were assessed using the two primary bacterial butyrate synthesis pathways, butyryl-CoA: acetate CoA-transferase (but) and butyrate kinase (buk) genes. Inactivity negatively affected fecal consistency and in combination with hypoxia aggravated the state of gut inflammation (p < 0.05). In contrast, gut permeability, various metabolic markers, the structure, diversity and abundance of butyrate producing microbial community were not significantly affected. Rearrangements in the butyrate producing microbial community structure were explained by experimental setup (13.4 %), experimentally structured metabolites (12.8 %) and gut metabolite-immunological markers (11.9 %), with 61.9% remaining unexplained. Many of the measured parameters were found to be correlated and were hence omitted from further analyses. The observed progressive increase in two immunological intestinal markers suggested that the transition from healthy physiological state towards the developed symptoms of low magnitude obesity-related syndromes was primarily driven by the onset of inactivity (lack of exercise in NBR) that were exacerbated by systemic hypoxia (HBR) and significantly alleviated by exercise, despite hypoxia (HAmb). Butyrate producing community in colon exhibited apparent resilience towards short-term modifications in host exercise or hypoxia. Progressive constipation (decreased intestinal motility) and increased local inflammation marker suggest that changes in microbial colonization and metabolism were taking place at the location of small intestine.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
We explored the assembly of intestinal microbiota in healthy male participants during the run-in (5 day) and experimental phases (21-day normoxic bed rest (NBR), hypoxic bedrest (HBR) and hypoxic ambulation (HAmb) in a strictly controlled laboratory environment, balanced fluid and dietary intakes, controlled circadian rhythm, microbial ambiental burden and 24/7 medical surveillance. The fraction of inspired O2 (FiO2) and partial pressure of inspired O2 (PiO2) were 0.209 and 133.1 ± 0.3 mmHg for NBR and 0.141 ± 0.004 and 90.0 ± 0.4 mmHg for both hypoxic variants (HBR and HAmb; ~4000 m simulated altitude), respectively. A number of parameters linked to intestinal transit spanning Bristol Stool Scale, defecation rates, zonulin, α1-antitrypsin, eosinophil derived neurotoxin, bile acids, reducing sugars, short chain fatty acids, total soluble organic carbon, water content, diet composition and food intake were measured (167 variables). The abundance, structure and diversity of butyrate producing microbial community were assessed using the two primary bacterial butyrate synthesis pathways, butyryl-CoA: acetate CoA-transferase (but) and butyrate kinase (buk) genes. Inactivity negatively affected fecal consistency and in combination with hypoxia aggravated the state of gut inflammation (p < 0.05). In contrast, gut permeability, various metabolic markers, the structure, diversity and abundance of butyrate producing microbial community were not significantly affected. Rearrangements in the butyrate producing microbial community structure were explained by experimental setup (13.4 %), experimentally structured metabolites (12.8 %) and gut metabolite-immunological markers (11.9 %), with 61.9% remaining unexplained. Many of the measured parameters were found to be correlated and were hence omitted from further analyses. The observed progressive increase in two immunological intestinal markers suggested that the transition from healthy physiological state towards the developed symptoms of low magnitude obesity-related syndromes was primarily driven by the onset of inactivity (lack of exercise in NBR) that were exacerbated by systemic hypoxia (HBR) and significantly alleviated by exercise, despite hypoxia (HAmb). Butyrate producing community in colon exhibited apparent resilience towards short-term modifications in host exercise or hypoxia. Progressive constipation (decreased intestinal motility) and increased local inflammation marker suggest that changes in microbial colonization and metabolism were taking place at the location of small intestine.
Proceedings Articles
Primož Lavrič; Žiga Emeršič; Blaž Meden; Vitomir Štruc; Peter Peer
Do it Yourself: Building a Low-Cost Iris Recognition System at Home Using Off-The-Shelf Components Proceedings Article
V: Electrotechnical and Computer Science Conference ERK 2017, 2017.
@inproceedings{ERK2017,
title = {Do it Yourself: Building a Low-Cost Iris Recognition System at Home Using Off-The-Shelf Components},
author = {Primož Lavrič and Žiga Emeršič and Blaž Meden and Vitomir Štruc and Peter Peer},
url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2019/08/lavricdo_it.pdf},
year = {2017},
date = {2017-09-01},
booktitle = {Electrotechnical and Computer Science Conference ERK 2017},
abstract = {Among the different biometric traits that can be used for person recognition, the human iris is generally consid-ered to be among the most accurate. However, despite a plethora of desirable characteristics, iris recognition is not widely as widely used as competing biometric modalities likely due to the high cost of existing commercial iris-recognition systems. In this paper we contribute towards the availability of low-cost iris recognition systems and present a prototype system built using off-the-shelf components. We describe the prototype device, the pipeline used for iris recognition, evaluate the performance of our solution on a small in-house dataset and discuss directions for future work. The current version of our prototype includes complete hardware and software implementations and has a combined bill-of-materials of 110 EUR.
},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Among the different biometric traits that can be used for person recognition, the human iris is generally consid-ered to be among the most accurate. However, despite a plethora of desirable characteristics, iris recognition is not widely as widely used as competing biometric modalities likely due to the high cost of existing commercial iris-recognition systems. In this paper we contribute towards the availability of low-cost iris recognition systems and present a prototype system built using off-the-shelf components. We describe the prototype device, the pipeline used for iris recognition, evaluate the performance of our solution on a small in-house dataset and discuss directions for future work. The current version of our prototype includes complete hardware and software implementations and has a combined bill-of-materials of 110 EUR.
Grm Klemen; Dobrišek Simon; Štruc Vitomir
Evaluating image superresolution algorithms for cross-resolution face recognition Proceedings Article
V: Proceedings of the Twenty-sixth International Electrotechnical and Computer Science Conference ERK 2017, 2017.
@inproceedings{ERK2017Grm,
title = {Evaluating image superresolution algorithms for cross-resolution face recognition},
author = {Grm Klemen and Dobrišek Simon and Štruc Vitomir},
url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2019/08/review_submission.pdf},
year = {2017},
date = {2017-09-01},
booktitle = {Proceedings of the Twenty-sixth International Electrotechnical and Computer Science Conference ERK 2017},
abstract = {With recent advancements in deep learning and convolutional neural networks (CNNs), face recognition has seen significant performance improvements over the last few years. However, low-resolution images still remain challenging, with CNNs performing relatively poorly compared to humans. One possibility to improve performance in these settings often advocated in the literature is the use of super-resolution (SR). In this paper, we explore the usefulness of SR algorithms for cross-resolution face recognition in experiments on the Labeled Faces in the Wild (LFW) and SCface datasets using four recent deep CNN models. We conduct experiments with synthetically down-sampled images as well as real-life low-resolution imagery captured by surveillance cameras. Our experiments show that image super-resolution can improve face recognition performance considerably on very low-resolution images (of size 24 x 24 or 32 x 32 pixels), when images are artificially down-sampled, but has a lesser (or sometimes even a detrimental) effect with real-life images leaving significant room for further research in this area.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
With recent advancements in deep learning and convolutional neural networks (CNNs), face recognition has seen significant performance improvements over the last few years. However, low-resolution images still remain challenging, with CNNs performing relatively poorly compared to humans. One possibility to improve performance in these settings often advocated in the literature is the use of super-resolution (SR). In this paper, we explore the usefulness of SR algorithms for cross-resolution face recognition in experiments on the Labeled Faces in the Wild (LFW) and SCface datasets using four recent deep CNN models. We conduct experiments with synthetically down-sampled images as well as real-life low-resolution imagery captured by surveillance cameras. Our experiments show that image super-resolution can improve face recognition performance considerably on very low-resolution images (of size 24 x 24 or 32 x 32 pixels), when images are artificially down-sampled, but has a lesser (or sometimes even a detrimental) effect with real-life images leaving significant room for further research in this area.
Novosel Rok; Meden Blaž; Emeršič Žiga; Štruc Vitomir; Peter Peer
Face recognition with Raspberry Pi for IoT Environments. Proceedings Article
V: Proceedings of the Twenty-sixth International Electrotechnical and Computer Science Conference ERK 2017, 2017.
@inproceedings{ERK2017c,
title = {Face recognition with Raspberry Pi for IoT Environments.},
author = {Novosel Rok and Meden Blaž and Emeršič Žiga and Štruc Vitomir and Peter Peer},
url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2019/08/novoselface_recognition.pdf},
year = {2017},
date = {2017-09-01},
booktitle = {Proceedings of the Twenty-sixth International Electrotechnical and Computer Science Conference ERK 2017},
abstract = {IoT has seen steady growth over recent years – smart home appliances, smart personal gear, personal assistants and many more. The same is true for the field of bio-metrics where the need for automatic and secure recognition schemes have spurred the development of fingerprint-and face-recognition mechanisms found today in most smart phones and similar hand-held devices. Devices used in the Internet of Things (IoT) are often low-powered with limited computational resources. This means that biomet-ric recognition pipelines aimed at IoT need to be streamlined and as efficient as possible. Towards this end, we describe in this paper how image-based biometrics can be leveraged in an IoT environment using a Raspberry Pi. We present a proof-of-concept web-based information system, secured by a face-recognition procedure, that gives authorized users access to potentially sensitive information.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
IoT has seen steady growth over recent years – smart home appliances, smart personal gear, personal assistants and many more. The same is true for the field of bio-metrics where the need for automatic and secure recognition schemes have spurred the development of fingerprint-and face-recognition mechanisms found today in most smart phones and similar hand-held devices. Devices used in the Internet of Things (IoT) are often low-powered with limited computational resources. This means that biomet-ric recognition pipelines aimed at IoT need to be streamlined and as efficient as possible. Towards this end, we describe in this paper how image-based biometrics can be leveraged in an IoT environment using a Raspberry Pi. We present a proof-of-concept web-based information system, secured by a face-recognition procedure, that gives authorized users access to potentially sensitive information.
Žiga Emeršič; Dejan Štepec; Vitomir Štruc; Peter Peer; Anjith George; Adii Ahmad; Elshibani Omar; Terrance E. Boult; Reza Safdaii; Yuxiang Zhou; others Stefanos Zafeiriou; Dogucan Yaman; Fevziye I. Eyoikur; Hazim K. Ekenel
The unconstrained ear recognition challenge Proceedings Article
V: 2017 IEEE International Joint Conference on Biometrics (IJCB), str. 715–724, IEEE 2017.
@inproceedings{emervsivc2017unconstrained,
title = {The unconstrained ear recognition challenge},
author = {Žiga Emeršič and Dejan Štepec and Vitomir Štruc and Peter Peer and Anjith George and Adii Ahmad and Elshibani Omar and Terrance E. Boult and Reza Safdaii and Yuxiang Zhou and others Stefanos Zafeiriou and Dogucan Yaman and Fevziye I. Eyoikur and Hazim K. Ekenel},
url = {https://arxiv.org/pdf/1708.06997.pdf},
year = {2017},
date = {2017-09-01},
booktitle = {2017 IEEE International Joint Conference on Biometrics (IJCB)},
pages = {715--724},
organization = {IEEE},
abstract = {In this paper we present the results o f the Unconstrained Ear Recognition Challenge (UERC), a group benchmarking effort centered around the problem o f person recognition from ear images captured in uncontrolled conditions. The goal o f the challenge was to assess the performance of existing ear recognition techniques on a challenging largescale dataset and identify open problems that need to be addressed in the future. Five groups from three continents participated in the challenge and contributed six ear recognition techniques fo r the evaluation, while multiple baselines were made available for the challenge by the UERC organizers. A comprehensive analysis was conducted with all participating approaches addressing essential research questions pertaining to the sensitivity o f the technology to head rotation, flipping, gallery size, large-scale recognition and others. The top performer o f the UERC was found to ensure robust performance on a smaller part o f the dataset (with 180 subjects) regardless o f image characteristics, but still exhibited a significant performance drop when the entire dataset comprising 3,704 subjects was used for testing.
},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper we present the results o f the Unconstrained Ear Recognition Challenge (UERC), a group benchmarking effort centered around the problem o f person recognition from ear images captured in uncontrolled conditions. The goal o f the challenge was to assess the performance of existing ear recognition techniques on a challenging largescale dataset and identify open problems that need to be addressed in the future. Five groups from three continents participated in the challenge and contributed six ear recognition techniques fo r the evaluation, while multiple baselines were made available for the challenge by the UERC organizers. A comprehensive analysis was conducted with all participating approaches addressing essential research questions pertaining to the sensitivity o f the technology to head rotation, flipping, gallery size, large-scale recognition and others. The top performer o f the UERC was found to ensure robust performance on a smaller part o f the dataset (with 180 subjects) regardless o f image characteristics, but still exhibited a significant performance drop when the entire dataset comprising 3,704 subjects was used for testing.
Žiga Emeršič; Dejan Štepec; Vitomir Štruc; Peter Peer
Training convolutional neural networks with limited training data for ear recognition in the wild Proceedings Article
V: IEEE International Conference on Automatic Face and Gesture Recognition, Workshop on Biometrics in the Wild 2017, 2017.
@inproceedings{emervsivc2017training,
title = {Training convolutional neural networks with limited training data for ear recognition in the wild},
author = {Žiga Emeršič and Dejan Štepec and Vitomir Štruc and Peter Peer},
url = {https://arxiv.org/pdf/1711.09952.pdf},
year = {2017},
date = {2017-05-01},
booktitle = {IEEE International Conference on Automatic Face and Gesture Recognition, Workshop on Biometrics in the Wild 2017},
journal = {arXiv preprint arXiv:1711.09952},
abstract = {Identity recognition from ear images is an active field of research within the biometric community. The ability to capture ear images from a distance and in a covert manner makes ear recognition technology an appealing choice for surveillance and security applications as well as related application domains. In contrast to other biometric modalities, where large datasets captured in uncontrolled settings are readily available, datasets of ear images are still limited in size and mostly of laboratory-like quality. As a consequence, ear recognition technology has not benefited yet from advances in deep learning and convolutional neural networks (CNNs) and is still lacking behind other modalities that experienced significant performance gains owing to deep recognition technology. In this paper we address this problem and aim at building a CNNbased ear recognition model. We explore different strategies towards model training with limited amounts of training data and show that by selecting an appropriate model architecture, using aggressive data augmentation and selective learning on existing (pre-trained) models, we are able to learn an effective CNN-based model using a little more than 1300 training images. The result of our work is the first CNN-based approach to ear recognition that is also made publicly available to the research community. With our model we are able to improve on the rank one recognition rate of the previous state-of-the-art by more than 25% on a challenging dataset of ear images captured from the web (a.k.a. in the wild).},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Identity recognition from ear images is an active field of research within the biometric community. The ability to capture ear images from a distance and in a covert manner makes ear recognition technology an appealing choice for surveillance and security applications as well as related application domains. In contrast to other biometric modalities, where large datasets captured in uncontrolled settings are readily available, datasets of ear images are still limited in size and mostly of laboratory-like quality. As a consequence, ear recognition technology has not benefited yet from advances in deep learning and convolutional neural networks (CNNs) and is still lacking behind other modalities that experienced significant performance gains owing to deep recognition technology. In this paper we address this problem and aim at building a CNNbased ear recognition model. We explore different strategies towards model training with limited amounts of training data and show that by selecting an appropriate model architecture, using aggressive data augmentation and selective learning on existing (pre-trained) models, we are able to learn an effective CNN-based model using a little more than 1300 training images. The result of our work is the first CNN-based approach to ear recognition that is also made publicly available to the research community. With our model we are able to improve on the rank one recognition rate of the previous state-of-the-art by more than 25% on a challenging dataset of ear images captured from the web (a.k.a. in the wild).
Ziga Emersic; Blaz Meden; Peter Peer; Vitornir Struc
Covariate analysis of descriptor-based ear recognition techniques Proceedings Article
V: 2017 international conference and workshop on bioinspired intelligence (IWOBI), str. 1–9, IEEE 2017.
@inproceedings{emersic2017covariate,
title = {Covariate analysis of descriptor-based ear recognition techniques},
author = {Ziga Emersic and Blaz Meden and Peter Peer and Vitornir Struc},
url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2019/08/Covariate_Analysis_of_Descriptor_based_Ear_Recognition_Techniques.pdf},
year = {2017},
date = {2017-01-01},
booktitle = {2017 international conference and workshop on bioinspired intelligence (IWOBI)},
pages = {1--9},
organization = {IEEE},
abstract = {Dense descriptor-based feature extraction techniques represent a popular choice for implementing biometric ear recognition system and are in general considered to be the current state-of-the-art in this area. In this paper, we study the impact of various factors (i.e., head rotation, presence of occlusions, gender and ethnicity) on the performance of 8 state-of-the-art descriptor-based ear recognition techniques. Our goal is to pinpoint weak points of the existing technology and identify open problems worth exploring in the future. We conduct our covariate analysis through identification experiments on the challenging AWE (Annotated Web Ears) dataset and report our findings. The results of our study show that high degrees of head movement and presence of accessories significantly impact the identification performance, whereas mild degrees of the listed factors and other covariates such as gender and ethnicity impact the identification performance only to a limited extent.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Dense descriptor-based feature extraction techniques represent a popular choice for implementing biometric ear recognition system and are in general considered to be the current state-of-the-art in this area. In this paper, we study the impact of various factors (i.e., head rotation, presence of occlusions, gender and ethnicity) on the performance of 8 state-of-the-art descriptor-based ear recognition techniques. Our goal is to pinpoint weak points of the existing technology and identify open problems worth exploring in the future. We conduct our covariate analysis through identification experiments on the challenging AWE (Annotated Web Ears) dataset and report our findings. The results of our study show that high degrees of head movement and presence of accessories significantly impact the identification performance, whereas mild degrees of the listed factors and other covariates such as gender and ethnicity impact the identification performance only to a limited extent.
Blaz Meden; Ziga Emersic; Vitomir Struc; Peter Peer
k-Same-Net: Neural-Network-Based Face Deidentification Proceedings Article
V: 2017 International Conference and Workshop on Bioinspired Intelligence (IWOBI), str. 1–7, IEEE 2017.
@inproceedings{meden2017kappa,
title = {k-Same-Net: Neural-Network-Based Face Deidentification},
author = {Blaz Meden and Ziga Emersic and Vitomir Struc and Peter Peer},
url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2019/08/k-same-net.pdf},
year = {2017},
date = {2017-01-01},
booktitle = {2017 International Conference and Workshop on Bioinspired Intelligence (IWOBI)},
pages = {1--7},
organization = {IEEE},
abstract = {An increasing amount of video and image data is being shared between government entities and other relevant stakeholders and requires careful handling of personal information. A popular approach for privacy protection in such data is the use of deidentification techniques, which aim at concealing the identity of individuals in the imagery while still preserving certain aspects of the data deidentification. In this work, we propose a novel approach towards face deidentification, called k-Same-Net, which combines recent generative neural networks (GNNs) with the well-known k-anonymity mechanism and provides formal guarantees regarding privacy protection on a closed set of identities. Our GNN is able to generate synthetic surrogate face images for dedentification by seamlessly combining features of identities used to train the GNN mode. furthermore, it allows us to guide the image-generation process with a small set of appearance-related parameters that can be used to alter specific aspects (e.g., facial expressions, age, gender) of the synthesized surrogate images. We demonstrate the feasibility of k-Same-Net in comparative experiments with competing techniques on the XM2VTS dataset and discuss the main characteristics of our approach.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
An increasing amount of video and image data is being shared between government entities and other relevant stakeholders and requires careful handling of personal information. A popular approach for privacy protection in such data is the use of deidentification techniques, which aim at concealing the identity of individuals in the imagery while still preserving certain aspects of the data deidentification. In this work, we propose a novel approach towards face deidentification, called k-Same-Net, which combines recent generative neural networks (GNNs) with the well-known k-anonymity mechanism and provides formal guarantees regarding privacy protection on a closed set of identities. Our GNN is able to generate synthetic surrogate face images for dedentification by seamlessly combining features of identities used to train the GNN mode. furthermore, it allows us to guide the image-generation process with a small set of appearance-related parameters that can be used to alter specific aspects (e.g., facial expressions, age, gender) of the synthesized surrogate images. We demonstrate the feasibility of k-Same-Net in comparative experiments with competing techniques on the XM2VTS dataset and discuss the main characteristics of our approach.
Abhijit Das; Umapada Pal; Miguel A Ferrer; Michael Blumenstein; Dejan Štepec; Peter Rot; Ziga Emeršič; Peter Peer; Vitomir Štruc; SV Aruna Kumar; Harish B S
SSERBC 2017: Sclera segmentation and eye recognition benchmarking competition Proceedings Article
V: 2017 IEEE International Joint Conference on Biometrics (IJCB), str. 742–747, IEEE 2017.
@inproceedings{das2017sserbc,
title = {SSERBC 2017: Sclera segmentation and eye recognition benchmarking competition},
author = {Abhijit Das and Umapada Pal and Miguel A Ferrer and Michael Blumenstein and Dejan Štepec and Peter Rot and Ziga Emeršič and Peter Peer and Vitomir Štruc and SV Aruna Kumar and Harish B S},
url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2019/08/SSERBC2017.pdf},
year = {2017},
date = {2017-01-01},
booktitle = {2017 IEEE International Joint Conference on Biometrics (IJCB)},
pages = {742--747},
organization = {IEEE},
abstract = {This paper summarises the results of the Sclera Segmentation and Eye Recognition Benchmarking Competition (SSERBC 2017). It was organised in the context of the International Joint Conference on Biometrics (IJCB 2017). The aim of this competition was to record the recent developments in sclera segmentation and eye recognition in the visible spectrum (using iris, sclera and peri-ocular, and their fusion), and also to gain the attention of researchers on this subject.
In this regard, we have used the Multi-Angle Sclera Dataset (MASD version 1). It is comprised of 2624 images taken from both the eyes of 82 identities. Therefore, it consists of images of 164 (82*2) eyes. A manual segmentation mask of these images was created to baseline both tasks.
Precision and recall based statistical measures were employed to evaluate the effectiveness of the segmentation and the ranks of the segmentation task. Recognition accuracy measure has been employed to measure the recognition task. Manually segmented sclera, iris and periocular regions were used in the recognition task. Sixteen teams registered for the competition, and among them, six teams submitted their algorithms or systems for the segmentation task and two of them submitted their recognition algorithm or systems.
The results produced by these algorithms or systems reflect current developments in the literature of sclera segmentation and eye recognition, employing cutting edge techniques. The MASD version 1 dataset with some of the ground truth will be freely available for research purposes. The success of the competition also demonstrates the recent interests of researchers from academia as well as industry on this subject},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper summarises the results of the Sclera Segmentation and Eye Recognition Benchmarking Competition (SSERBC 2017). It was organised in the context of the International Joint Conference on Biometrics (IJCB 2017). The aim of this competition was to record the recent developments in sclera segmentation and eye recognition in the visible spectrum (using iris, sclera and peri-ocular, and their fusion), and also to gain the attention of researchers on this subject.
In this regard, we have used the Multi-Angle Sclera Dataset (MASD version 1). It is comprised of 2624 images taken from both the eyes of 82 identities. Therefore, it consists of images of 164 (82*2) eyes. A manual segmentation mask of these images was created to baseline both tasks.
Precision and recall based statistical measures were employed to evaluate the effectiveness of the segmentation and the ranks of the segmentation task. Recognition accuracy measure has been employed to measure the recognition task. Manually segmented sclera, iris and periocular regions were used in the recognition task. Sixteen teams registered for the competition, and among them, six teams submitted their algorithms or systems for the segmentation task and two of them submitted their recognition algorithm or systems.
The results produced by these algorithms or systems reflect current developments in the literature of sclera segmentation and eye recognition, employing cutting edge techniques. The MASD version 1 dataset with some of the ground truth will be freely available for research purposes. The success of the competition also demonstrates the recent interests of researchers from academia as well as industry on this subject
In this regard, we have used the Multi-Angle Sclera Dataset (MASD version 1). It is comprised of 2624 images taken from both the eyes of 82 identities. Therefore, it consists of images of 164 (82*2) eyes. A manual segmentation mask of these images was created to baseline both tasks.
Precision and recall based statistical measures were employed to evaluate the effectiveness of the segmentation and the ranks of the segmentation task. Recognition accuracy measure has been employed to measure the recognition task. Manually segmented sclera, iris and periocular regions were used in the recognition task. Sixteen teams registered for the competition, and among them, six teams submitted their algorithms or systems for the segmentation task and two of them submitted their recognition algorithm or systems.
The results produced by these algorithms or systems reflect current developments in the literature of sclera segmentation and eye recognition, employing cutting edge techniques. The MASD version 1 dataset with some of the ground truth will be freely available for research purposes. The success of the competition also demonstrates the recent interests of researchers from academia as well as industry on this subject
2016
Journal Articles
Jaka Kravanja; Mario Žganec; Jerneja Žganec-Gros; Simon Dobrišek; Vitomir Štruc
Robust Depth Image Acquisition Using Modulated Pattern Projection and Probabilistic Graphical Models Članek v strokovni reviji
V: Sensors, vol. 16, no. 10, str. 1740, 2016.
@article{kravanja2016robust,
title = {Robust Depth Image Acquisition Using Modulated Pattern Projection and Probabilistic Graphical Models},
author = {Jaka Kravanja and Mario Žganec and Jerneja Žganec-Gros and Simon Dobrišek and Vitomir Štruc},
url = {https://lmi.fe.uni-lj.si/en/robustdepthimageacquisitionusingmodulatedpatternprojectionandprobabilisticgraphicalmodels-2/},
doi = {10.3390/s16101740},
year = {2016},
date = {2016-10-20},
urldate = {2016-10-20},
journal = {Sensors},
volume = {16},
number = {10},
pages = {1740},
publisher = {Multidisciplinary Digital Publishing Institute},
abstract = {Depth image acquisition with structured light approaches in outdoor environments is a challenging problem due to external factors, such as ambient sunlight, which commonly affect the acquisition procedure. This paper presents a novel structured light sensor designed specifically for operation in outdoor environments. The sensor exploits a modulated sequence of structured light projected onto the target scene to counteract environmental factors and estimate a spatial distortion map in a robust manner. The correspondence between the projected pattern and the estimated distortion map is then established using a probabilistic framework based on graphical models. Finally, the depth image of the target scene is reconstructed using a number of reference frames recorded during the calibration process. We evaluate the proposed sensor on experimental data in indoor and outdoor environments and present comparative experiments with other existing methods, as well as commercial sensors.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Depth image acquisition with structured light approaches in outdoor environments is a challenging problem due to external factors, such as ambient sunlight, which commonly affect the acquisition procedure. This paper presents a novel structured light sensor designed specifically for operation in outdoor environments. The sensor exploits a modulated sequence of structured light projected onto the target scene to counteract environmental factors and estimate a spatial distortion map in a robust manner. The correspondence between the projected pattern and the estimated distortion map is then established using a probabilistic framework based on graphical models. Finally, the depth image of the target scene is reconstructed using a number of reference frames recorded during the calibration process. We evaluate the proposed sensor on experimental data in indoor and outdoor environments and present comparative experiments with other existing methods, as well as commercial sensors.
Jaka Kravanja; Mario Žganec; Jerneja Žganec-Gros; Simon Dobrišek; Vitomir Štruc
Exploiting Spatio-Temporal Information for Light-Plane Labeling in Depth-Image Sensors Using Probabilistic Graphical Models Članek v strokovni reviji
V: Informatica, vol. 27, no. 1, str. 67–84, 2016.
@article{kravanja2016exploiting,
title = {Exploiting Spatio-Temporal Information for Light-Plane Labeling in Depth-Image Sensors Using Probabilistic Graphical Models},
author = {Jaka Kravanja and Mario Žganec and Jerneja Žganec-Gros and Simon Dobrišek and Vitomir Štruc},
url = {https://lmi.fe.uni-lj.si/en/exploitingspatio-temporalinformationforlight-planelabelingindepth-imagesensorsusingprobabilisticgraphicalmodels/},
year = {2016},
date = {2016-03-30},
urldate = {2016-03-30},
journal = {Informatica},
volume = {27},
number = {1},
pages = {67--84},
publisher = {Vilnius University Institute of Mathematics and Informatics},
abstract = {This paper proposes a novel approach to light plane labeling in depth-image sensors relying on “uncoded” structured light. The proposed approach adopts probabilistic graphical models (PGMs) to solve the correspondence problem between the projected and the detected light patterns. The procedure for solving the correspondence problem is designed to take the spatial relations between the parts of the projected pattern and prior knowledge about the structure of the pattern into account, but it also exploits temporal information to achieve reliable light-plane labeling. The procedure is assessed on a database of light patterns detected with a specially developed imaging sensor that, unlike most existing solutions on the market, was shown to work reliably in outdoor environments as well as in the presence of other identical (active) sensors directed at the same scene. The results of our experiments show that the proposed approach is able to reliably solve the correspondence problem and assign light-plane labels to the detected pattern with a high accuracy, even when large spatial discontinuities are present in the observed scene.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This paper proposes a novel approach to light plane labeling in depth-image sensors relying on “uncoded” structured light. The proposed approach adopts probabilistic graphical models (PGMs) to solve the correspondence problem between the projected and the detected light patterns. The procedure for solving the correspondence problem is designed to take the spatial relations between the parts of the projected pattern and prior knowledge about the structure of the pattern into account, but it also exploits temporal information to achieve reliable light-plane labeling. The procedure is assessed on a database of light patterns detected with a specially developed imaging sensor that, unlike most existing solutions on the market, was shown to work reliably in outdoor environments as well as in the presence of other identical (active) sensors directed at the same scene. The results of our experiments show that the proposed approach is able to reliably solve the correspondence problem and assign light-plane labels to the detected pattern with a high accuracy, even when large spatial discontinuities are present in the observed scene.
Proceedings Articles
Walter Scheirer; Patrick Flynn; Changxing Ding; Guodong Guo; Vitomir Štruc; Mohamad Al Jazaery; Simon Dobrišek; Klemen Grm; Dacheng Tao; Yu Zhu; Joel Brogan; Sandipan Banerjee; Aparna Bharati; Brandon Richard Webster
Report on the BTAS 2016 Video Person Recognition Evaluation Proceedings Article
V: Proceedings of the IEEE International Conference on Biometrics: Theory, Applications ans Systems (BTAS), IEEE, 2016.
@inproceedings{BTAS2016,
title = {Report on the BTAS 2016 Video Person Recognition Evaluation},
author = {Walter Scheirer and Patrick Flynn and Changxing Ding and Guodong Guo and Vitomir Štruc and Mohamad Al Jazaery and Simon Dobrišek and Klemen Grm and Dacheng Tao and Yu Zhu and Joel Brogan and Sandipan Banerjee and Aparna Bharati and Brandon Richard Webster},
year = {2016},
date = {2016-10-05},
booktitle = {Proceedings of the IEEE International Conference on Biometrics: Theory, Applications ans Systems (BTAS)},
publisher = {IEEE},
abstract = {This report presents results from the Video Person Recognition Evaluation held in conjunction with the 8th IEEE International Conference on Biometrics: Theory, Applications, and Systems (BTAS). Two experiments required algorithms to recognize people in videos from the Pointand- Shoot Face Recognition Challenge Problem (PaSC). The first consisted of videos from a tripod mounted high quality video camera. The second contained videos acquired from 5 different handheld video cameras. There were 1,401 videos in each experiment of 265 subjects. The subjects, the scenes, and the actions carried out by the people are the same in both experiments. An additional experiment required algorithms to recognize people in videos from the Video Database of Moving Faces and People (VDMFP). There were 958 videos in this experiment of 297 subjects. Four groups from around the world participated in the evaluation. The top verification rate for PaSC from this evaluation is 0:98 at a false accept rate of 0:01 — a remarkable advancement in performance from the competition held at FG 2015.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
This report presents results from the Video Person Recognition Evaluation held in conjunction with the 8th IEEE International Conference on Biometrics: Theory, Applications, and Systems (BTAS). Two experiments required algorithms to recognize people in videos from the Pointand- Shoot Face Recognition Challenge Problem (PaSC). The first consisted of videos from a tripod mounted high quality video camera. The second contained videos acquired from 5 different handheld video cameras. There were 1,401 videos in each experiment of 265 subjects. The subjects, the scenes, and the actions carried out by the people are the same in both experiments. An additional experiment required algorithms to recognize people in videos from the Video Database of Moving Faces and People (VDMFP). There were 958 videos in this experiment of 297 subjects. Four groups from around the world participated in the evaluation. The top verification rate for PaSC from this evaluation is 0:98 at a false accept rate of 0:01 — a remarkable advancement in performance from the competition held at FG 2015.
Janez Križaj; Simon Dobrišek; France Mihelič; Vitomir Štruc
Facial Landmark Localization from 3D Images Proceedings Article
V: Proceedings of the Electrotechnical and Computer Science Conference (ERK), Portorož, Slovenia, 2016.
@inproceedings{ERK2016Janez,
title = {Facial Landmark Localization from 3D Images},
author = {Janez Križaj and Simon Dobrišek and France Mihelič and Vitomir Štruc},
year = {2016},
date = {2016-09-20},
booktitle = {Proceedings of the Electrotechnical and Computer Science Conference (ERK)},
address = {Portorož, Slovenia},
abstract = {A novel method for automatic facial landmark localization is presented. The method builds on the supervised descent framework, which was shown to successfully localize landmarks in the presence of large expression variations and mild occlusions, but struggles when localizing landmarks on faces with large pose variations. We propose an extension of the supervised descent framework which trains multiple descent maps and results in increased robustness to pose variations. The performance of the proposed method is demonstrated on the Bosphorus database for the problem of facial landmark localization from 3D data. Our experimental results show that the proposed method exhibits increased robustness to pose variations, while retaining high performance in the case of expression and occlusion variations.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
A novel method for automatic facial landmark localization is presented. The method builds on the supervised descent framework, which was shown to successfully localize landmarks in the presence of large expression variations and mild occlusions, but struggles when localizing landmarks on faces with large pose variations. We propose an extension of the supervised descent framework which trains multiple descent maps and results in increased robustness to pose variations. The performance of the proposed method is demonstrated on the Bosphorus database for the problem of facial landmark localization from 3D data. Our experimental results show that the proposed method exhibits increased robustness to pose variations, while retaining high performance in the case of expression and occlusion variations.
Sebastjan Fabijan; Vitomir Štruc
Vpliv registracije obraznih področij na učinkovitost samodejnega razpoznavanja obrazov: študija z OpenBR Proceedings Article
V: Proceedings of the Electrotechnical and Computer Science Conference (ERK), 2016.
@inproceedings{ERK2016_Seba,
title = {Vpliv registracije obraznih področij na učinkovitost samodejnega razpoznavanja obrazov: študija z OpenBR},
author = {Sebastjan Fabijan and Vitomir Štruc},
url = {https://lmi.fe.uni-lj.si/en/vplivregistracijeobraznihpodrocijnaucinkovitostsamodejnegarazpoznavanjaobrazovstudijazopenbr/},
year = {2016},
date = {2016-09-20},
urldate = {2016-09-20},
booktitle = {Proceedings of the Electrotechnical and Computer Science Conference (ERK)},
abstract = {Razpoznavanje obrazov je v zadnjih letih postalo eno najuspešnejših področij samodejne, računalniško podprte analize slik, ki se lahko pohvali z različnimi primeri upor-abe v praksi. Enega ključnih korakav za uspešno razpoznavanje predstavlja poravnava obrazov na slikah. S poravnavo poskušamo zagotoviti neodvisnost razpozn-av-an-ja od sprememb zornih kotov pri zajemu slike, ki v slikovne podatke vnašajo visoko stopnjo variabilnosti. V prispevku predstavimo tri postopke poravnavanja obrazov (iz literature) in proučimo njihov vpliv na uspešnost razpoznavanja s postopki, udejanjenimi v odprtokodnem programskem ogrodju Open Source Biometric Recognition (OpenBR). Vse poizkuse izvedemo na podatkovni zbirki Labeled Faces in the Wild (LFW).},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Razpoznavanje obrazov je v zadnjih letih postalo eno najuspešnejših področij samodejne, računalniško podprte analize slik, ki se lahko pohvali z različnimi primeri upor-abe v praksi. Enega ključnih korakav za uspešno razpoznavanje predstavlja poravnava obrazov na slikah. S poravnavo poskušamo zagotoviti neodvisnost razpozn-av-an-ja od sprememb zornih kotov pri zajemu slike, ki v slikovne podatke vnašajo visoko stopnjo variabilnosti. V prispevku predstavimo tri postopke poravnavanja obrazov (iz literature) in proučimo njihov vpliv na uspešnost razpoznavanja s postopki, udejanjenimi v odprtokodnem programskem ogrodju Open Source Biometric Recognition (OpenBR). Vse poizkuse izvedemo na podatkovni zbirki Labeled Faces in the Wild (LFW).
Žiga Stržinar; Klemen Grm; Vitomir Štruc
Učenje podobnosti v globokih nevronskih omrežjih za razpoznavanje obrazov Proceedings Article
V: Proceedings of the Electrotechnical and Computer Science Conference (ERK), Portorož, Slovenia, 2016.
@inproceedings{ERK2016_sebastjan,
title = {Učenje podobnosti v globokih nevronskih omrežjih za razpoznavanje obrazov},
author = {Žiga Stržinar and Klemen Grm and Vitomir Štruc},
url = {https://lmi.fe.uni-lj.si/en/ucenjepodobnostivglobokihnevronskihomrezjihzarazpoznavanjeobrazov/},
year = {2016},
date = {2016-09-20},
urldate = {2016-09-20},
booktitle = {Proceedings of the Electrotechnical and Computer Science Conference (ERK)},
address = {Portorož, Slovenia},
abstract = {Učenje podobnosti med pari vhodnih slik predstavlja enega najpopularnejših pristopov k razpoznavanju na področju globokega učenja. Pri tem pristopu globoko nevronsko omrežje na vhodu sprejme par slik (obrazov) in na izhodu vrne mero podobnosti med vhodnima slikama, ki jo je moč uporabiti za razpoznavanje. Izračun podobnosti je pri tem lahko v celoti udejanjen z globokim omrežjem, lahko pa se omrežje uporabi zgolj za izračun predstavitve vhodnega para slik, preslikava iz izračunane predstavitve v mero podobnosti pa se izvede z drugim, potencialno primernejšim modelom. V tem prispevku preizkusimo 5 različnih modelov za izvedbo preslikave med izračunano predstavitvijo in mero podobnosti, pri čemer za poizkuse uporabimo lastno nevronsko omrežje. Rezultati naših eksperimentov na problemu razpoznavanja obrazov kažejo na pomembnost izbire primernega modela, saj so razlike med uspešnostjo razpoznavanje od modela do modela precejšnje.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Učenje podobnosti med pari vhodnih slik predstavlja enega najpopularnejših pristopov k razpoznavanju na področju globokega učenja. Pri tem pristopu globoko nevronsko omrežje na vhodu sprejme par slik (obrazov) in na izhodu vrne mero podobnosti med vhodnima slikama, ki jo je moč uporabiti za razpoznavanje. Izračun podobnosti je pri tem lahko v celoti udejanjen z globokim omrežjem, lahko pa se omrežje uporabi zgolj za izračun predstavitve vhodnega para slik, preslikava iz izračunane predstavitve v mero podobnosti pa se izvede z drugim, potencialno primernejšim modelom. V tem prispevku preizkusimo 5 različnih modelov za izvedbo preslikave med izračunano predstavitvijo in mero podobnosti, pri čemer za poizkuse uporabimo lastno nevronsko omrežje. Rezultati naših eksperimentov na problemu razpoznavanja obrazov kažejo na pomembnost izbire primernega modela, saj so razlike med uspešnostjo razpoznavanje od modela do modela precejšnje.
Simon Dobrišek; David Čefarin; Vitomir Štruc; France Mihelič
Assessment of the Google Speech Application Programming Interface for Automatic Slovenian Speech Recognition Proceedings Article
V: Jezikovne Tehnologije in Digitalna Humanistika, 2016.
@inproceedings{SJDT,
title = {Assessment of the Google Speech Application Programming Interface for Automatic Slovenian Speech Recognition},
author = {Simon Dobrišek and David Čefarin and Vitomir Štruc and France Mihelič},
url = {https://lmi.fe.uni-lj.si/en/assessmentofthegooglespeechapplicationprogramminginterfaceforautomaticslovenianspeechrecognition/},
year = {2016},
date = {2016-09-20},
urldate = {2016-09-20},
booktitle = {Jezikovne Tehnologije in Digitalna Humanistika},
abstract = {Automatic speech recognizers are slowly maturing into technologies that enable humans to communicate more naturally and effectively with a variety of smart devices and information-communication systems. Large global companies such as Google, Microsoft, Apple, IBM and Baidu compete in developing the most reliable speech recognizers, supporting as many of the main world languages as possible. Due to the relatively small number of speakers, the support for the Slovenian spoken language is lagging behind, and among the major global companies only Google has recently supported our spoken language. The paper presents the results of our independent assessment of the Google speech-application programming interface for automatic Slovenian speech recognition. For the experiments, we used speech databases that are otherwise used for the development and assessment of Slovenian speech recognizers.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Automatic speech recognizers are slowly maturing into technologies that enable humans to communicate more naturally and effectively with a variety of smart devices and information-communication systems. Large global companies such as Google, Microsoft, Apple, IBM and Baidu compete in developing the most reliable speech recognizers, supporting as many of the main world languages as possible. Due to the relatively small number of speakers, the support for the Slovenian spoken language is lagging behind, and among the major global companies only Google has recently supported our spoken language. The paper presents the results of our independent assessment of the Google speech-application programming interface for automatic Slovenian speech recognition. For the experiments, we used speech databases that are otherwise used for the development and assessment of Slovenian speech recognizers.
Metod Ribič; Žiga Emeršič; Vitomir Štruc; Peter Peer
Influence of alignment on ear recognition : case study on AWE Dataset Proceedings Article
V: Proceedings of the Electrotechnical and Computer Science Conference (ERK), str. 131-134, Portorož, Slovenia, 2016.
@inproceedings{RibicERK2016,
title = {Influence of alignment on ear recognition : case study on AWE Dataset},
author = {Metod Ribič and Žiga Emeršič and Vitomir Štruc and Peter Peer},
url = {https://lmi.fe.uni-lj.si/en/influenceofalignmentonearrecognitioncasestudyonawedataset/},
year = {2016},
date = {2016-09-20},
urldate = {2016-09-20},
booktitle = {Proceedings of the Electrotechnical and Computer Science Conference (ERK)},
pages = {131-134},
address = {Portorož, Slovenia},
abstract = {Ear as a biometric modality presents a viable source for automatic human recognition. In recent years local description methods have been gaining on popularity due to their invariance to illumination and occlusion. However, these methods require that images are well aligned and preprocessed as good as possible. This causes one of the greatest challenges of ear recognition: sensitivity to pose variations. Recently, we presented Annotated Web Ears dataset that opens new challenges in ear recognition. In this paper we test the influence of alignment on recognition performance and prove that even with the alignment the database is still very challenging, even-though the recognition rate is improved due to alignment. We also prove that more sophisticated alignment methods are needed to address the AWE dataset efficiently},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Ear as a biometric modality presents a viable source for automatic human recognition. In recent years local description methods have been gaining on popularity due to their invariance to illumination and occlusion. However, these methods require that images are well aligned and preprocessed as good as possible. This causes one of the greatest challenges of ear recognition: sensitivity to pose variations. Recently, we presented Annotated Web Ears dataset that opens new challenges in ear recognition. In this paper we test the influence of alignment on recognition performance and prove that even with the alignment the database is still very challenging, even-though the recognition rate is improved due to alignment. We also prove that more sophisticated alignment methods are needed to address the AWE dataset efficiently
Simon Dobrišek; David Čefarin; Vitomir Štruc; France Mihelič
Preizkus Googlovega govornega programskega vmesnika pri samodejnem razpoznavanju govorjene slovenščine Proceedings Article
V: Jezikovne tehnologije in digitalna humanistika, str. 47-51, 2016.
@inproceedings{dobrivsekpreizkus,
title = {Preizkus Googlovega govornega programskega vmesnika pri samodejnem razpoznavanju govorjene slovenščine},
author = {Simon Dobrišek and David Čefarin and Vitomir Štruc and France Mihelič},
url = {http://www.sdjt.si/wp/wp-content/uploads/2016/09/JTDH-2016_Dobrisek-et-al_Preizkus-Googlovega-govornega-programskega-vmesnika.pdf},
year = {2016},
date = {2016-09-01},
booktitle = {Jezikovne tehnologije in digitalna humanistika},
pages = {47-51},
abstract = {Automatic speech recognizers are slowly maturing into technologies that enable humans to communicate more naturally and effectively with a variety of smart devices and information-communication systems. Large global companies such as Google, Microsoft, Apple, IBM and Baidu compete in developing the most reliable speech recognizers, supporting as many of the main world languages as possible. Due to the relatively small number of speakers, the support for the Slovenian spoken language is lagging behind, and among the major global companies only Google has recently supported our spoken language. The paper presents the results of our independent assessment of the Google speech-application programming interface for automatic Slovenian speech recognition. For the experiments, we used speech databases that are otherwise used for the development and assessment of Slovenian speech recognizers.
},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Automatic speech recognizers are slowly maturing into technologies that enable humans to communicate more naturally and effectively with a variety of smart devices and information-communication systems. Large global companies such as Google, Microsoft, Apple, IBM and Baidu compete in developing the most reliable speech recognizers, supporting as many of the main world languages as possible. Due to the relatively small number of speakers, the support for the Slovenian spoken language is lagging behind, and among the major global companies only Google has recently supported our spoken language. The paper presents the results of our independent assessment of the Google speech-application programming interface for automatic Slovenian speech recognition. For the experiments, we used speech databases that are otherwise used for the development and assessment of Slovenian speech recognizers.
Klemen Grm; Simon Dobrišek; Vitomir Štruc
Deep pair-wise similarity learning for face recognition Proceedings Article
V: 4th International Workshop on Biometrics and Forensics (IWBF), str. 1–6, IEEE 2016.
@inproceedings{grm2016deep,
title = {Deep pair-wise similarity learning for face recognition},
author = {Klemen Grm and Simon Dobrišek and Vitomir Štruc},
url = {https://lmi.fe.uni-lj.si/en/deeppair-wisesimilaritylearningforfacerecognition/},
year = {2016},
date = {2016-01-01},
urldate = {2016-01-01},
booktitle = {4th International Workshop on Biometrics and Forensics (IWBF)},
pages = {1--6},
organization = {IEEE},
abstract = {Recent advances in deep learning made it possible to build deep hierarchical models capable of delivering state-of-the-art performance in various vision tasks, such as object recognition, detection or tracking. For recognition tasks the most common approach when using deep models is to learn object representations (or features) directly from raw image-input and then feed the learned features to a suitable classifier. Deep models used in this pipeline are typically heavily parameterized and require enormous amounts of training data to deliver competitive recognition performance. Despite the use of data augmentation techniques, many application domains, predefined experimental protocols or specifics of the recognition problem limit the amount of available training data and make training an effective deep hierarchical model a difficult task. In this paper, we present a novel, deep pair-wise similarity learning (DPSL) strategy for deep models, developed specifically to overcome the problem of insufficient training data, and demonstrate its usage on the task of face recognition. Unlike existing (deep) learning strategies, DPSL operates on image-pairs and tries to learn pair-wise image similarities that can be used for recognition purposes directly instead of feature representations that need to be fed to appropriate classification techniques, as with traditional deep learning pipelines. Since our DPSL strategy assumes an image pair as the input to the learning procedure, the amount of training data available to train deep models is quadratic in the number of available training images, which is of paramount importance for models with a large number of parameters. We demonstrate the efficacy of the proposed learning strategy by developing a deep model for pose-invariant face recognition, called Pose-Invariant Similarity Index (PISI), and presenting comparative experimental results on the FERET an IJB-A datasets.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Recent advances in deep learning made it possible to build deep hierarchical models capable of delivering state-of-the-art performance in various vision tasks, such as object recognition, detection or tracking. For recognition tasks the most common approach when using deep models is to learn object representations (or features) directly from raw image-input and then feed the learned features to a suitable classifier. Deep models used in this pipeline are typically heavily parameterized and require enormous amounts of training data to deliver competitive recognition performance. Despite the use of data augmentation techniques, many application domains, predefined experimental protocols or specifics of the recognition problem limit the amount of available training data and make training an effective deep hierarchical model a difficult task. In this paper, we present a novel, deep pair-wise similarity learning (DPSL) strategy for deep models, developed specifically to overcome the problem of insufficient training data, and demonstrate its usage on the task of face recognition. Unlike existing (deep) learning strategies, DPSL operates on image-pairs and tries to learn pair-wise image similarities that can be used for recognition purposes directly instead of feature representations that need to be fed to appropriate classification techniques, as with traditional deep learning pipelines. Since our DPSL strategy assumes an image pair as the input to the learning procedure, the amount of training data available to train deep models is quadratic in the number of available training images, which is of paramount importance for models with a large number of parameters. We demonstrate the efficacy of the proposed learning strategy by developing a deep model for pose-invariant face recognition, called Pose-Invariant Similarity Index (PISI), and presenting comparative experimental results on the FERET an IJB-A datasets.
Žiga Golob; Jerneja Žganec Gros; Vitomir Štruc; France Mihelič; Simon Dobrišek
A Composition Algorithm of Compact Finite-State Super Transducers for Grapheme-to-Phoneme Conversion Proceedings Article
V: International Conference on Text, Speech, and Dialogue, str. 375–382, Springer 2016.
@inproceedings{golob2016composition,
title = {A Composition Algorithm of Compact Finite-State Super Transducers for Grapheme-to-Phoneme Conversion},
author = {Žiga Golob and Jerneja Žganec Gros and Vitomir Štruc and France Mihelič and Simon Dobrišek},
year = {2016},
date = {2016-01-01},
booktitle = {International Conference on Text, Speech, and Dialogue},
pages = {375--382},
organization = {Springer},
abstract = {Minimal deterministic finite-state transducers (MDFSTs) are powerful models that can be used to represent pronunciation dictionaries in a compact form. Intuitively, we would assume that by increasing the size of the dictionary, the size of the MDFSTs would increase as well. However, as we show in the paper, this intuition does not hold for highly inflected languages. With such languages the size of the MDFSTs begins to decrease once the number of words in the represented dictionary reaches a certain threshold. Motivated by this observation, we have developed a new type of FST, called a finite-state super transducer (FSST), and show experimentally that the FSST is capable of representing pronunciation dictionaries with fewer states and transitions than MDFSTs. Furthermore, we show that (unlike MDFSTs) our FSSTs can also accept words that are not part of the represented dictionary. The phonetic transcriptions of these out-of-dictionary words may not always be correct, but the observed error rates are comparable to the error rates of the traditional methods for grapheme-to-phoneme conversion.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Minimal deterministic finite-state transducers (MDFSTs) are powerful models that can be used to represent pronunciation dictionaries in a compact form. Intuitively, we would assume that by increasing the size of the dictionary, the size of the MDFSTs would increase as well. However, as we show in the paper, this intuition does not hold for highly inflected languages. With such languages the size of the MDFSTs begins to decrease once the number of words in the represented dictionary reaches a certain threshold. Motivated by this observation, we have developed a new type of FST, called a finite-state super transducer (FSST), and show experimentally that the FSST is capable of representing pronunciation dictionaries with fewer states and transitions than MDFSTs. Furthermore, we show that (unlike MDFSTs) our FSSTs can also accept words that are not part of the represented dictionary. The phonetic transcriptions of these out-of-dictionary words may not always be correct, but the observed error rates are comparable to the error rates of the traditional methods for grapheme-to-phoneme conversion.
2015
Journal Articles
Boštjan Murovec
Job-shop local-search move evaluation without direct consideration of the criterion’s value Članek v strokovni reviji
V: European Journal of Operational Research, vol. 241, no. 2, str. 320 - 329, 2015, ISSN: 0377-2217.
@article{MUROVEC2015320,
title = {Job-shop local-search move evaluation without direct consideration of the criterion’s value},
author = {Boštjan Murovec},
url = {http://www.sciencedirect.com/science/article/pii/S0377221714007309},
doi = {https://doi.org/10.1016/j.ejor.2014.08.044},
issn = {0377-2217},
year = {2015},
date = {2015-01-01},
journal = {European Journal of Operational Research},
volume = {241},
number = {2},
pages = {320 - 329},
abstract = {This article focuses on the evaluation of moves for the local search of the job-shop problem with the makespan criterion. We reason that the omnipresent ranking of moves according to their resulting value of a criterion function makes the local search unnecessarily myopic. Consequently, we introduce an alternative evaluation that relies on a surrogate quantity of the move’s potential, which is related to, but not strongly coupled with, the bare criterion. The approach is confirmed by empirical tests, where the proposed evaluator delivers a new upper bound on the well-known benchmark test yn2. The line of the argumentation also shows that by sacrificing accuracy the established makespan estimators unintentionally improve on the move evaluation in comparison to the exact makespan calculation, in contrast to the belief that the reliance on estimation degrades the optimization results.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This article focuses on the evaluation of moves for the local search of the job-shop problem with the makespan criterion. We reason that the omnipresent ranking of moves according to their resulting value of a criterion function makes the local search unnecessarily myopic. Consequently, we introduce an alternative evaluation that relies on a surrogate quantity of the move’s potential, which is related to, but not strongly coupled with, the bare criterion. The approach is confirmed by empirical tests, where the proposed evaluator delivers a new upper bound on the well-known benchmark test yn2. The line of the argumentation also shows that by sacrificing accuracy the established makespan estimators unintentionally improve on the move evaluation in comparison to the exact makespan calculation, in contrast to the belief that the reliance on estimation degrades the optimization results.
Boštjan Murovec; Sabina Kolbl; Blaž Stres
Methane Yield Database: Online infrastructure and bioresource for methane yield data and related metadata Članek v strokovni reviji
V: Bioresource Technology, vol. 189, str. 217 - 223, 2015, ISSN: 0960-8524.
@article{MUROVEC2015217,
title = {Methane Yield Database: Online infrastructure and bioresource for methane yield data and related metadata},
author = {Boštjan Murovec and Sabina Kolbl and Blaž Stres},
url = {http://www.sciencedirect.com/science/article/pii/S0960852415005040},
doi = {https://doi.org/10.1016/j.biortech.2015.04.021},
issn = {0960-8524},
year = {2015},
date = {2015-01-01},
journal = {Bioresource Technology},
volume = {189},
pages = {217 - 223},
abstract = {The aim of this study was to develop and validate a community supported online infrastructure and bioresource for methane yield data and accompanying metadata collected from published literature. In total, 1164 entries described by 15,749 data points were assembled. Analysis of data collection showed little congruence in reporting of methodological approaches. The largest identifiable source of variation in reported methane yields was represented by authorship (i.e. substrate batches within particular substrate class) within which experimental scales (volumes (0.02–5l), incubation temperature (34–40°C) and % VS of substrate played an important role (p<0.0},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The aim of this study was to develop and validate a community supported online infrastructure and bioresource for methane yield data and accompanying metadata collected from published literature. In total, 1164 entries described by 15,749 data points were assembled. Analysis of data collection showed little congruence in reporting of methodological approaches. The largest identifiable source of variation in reported methane yields was represented by authorship (i.e. substrate batches within particular substrate class) within which experimental scales (volumes (0.02–5l), incubation temperature (34–40°C) and % VS of substrate played an important role (p<0.0
Gemma Henderson; Faith Cox; Siva Ganesh; Arjan Jonker; Wayne Young; Peter H Janssen
Rumen microbial community composition varies with diet and host, but a core microbiome is found across a wide geographical range Članek v strokovni reviji
V: Scientific reports, vol. art 14567, no. 5, str. 1–13, 2015, ISSN: 2045-2322.
@article{Henderson_Cox_Ganesh_Jonker_Young_Janssen_2015,
title = {Rumen microbial community composition varies with diet and host, but a core microbiome is found across a wide geographical range},
author = {Gemma Henderson and Faith Cox and Siva Ganesh and Arjan Jonker and Wayne Young and Peter H Janssen},
url = {http://www.nature.com/articles/srep14567},
doi = {10.1038/srep14567},
issn = {2045-2322},
year = {2015},
date = {2015-01-01},
journal = {Scientific reports},
volume = {art 14567},
number = {5},
pages = {1–13},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Proceedings Articles
Klemen Grm; Simon Dobrišek; Vitomir Štruc
The pose-invariant similarity index for face recognition Proceedings Article
V: Proceedings of the Electrotechnical and Computer Science Conference (ERK), Portorož, Slovenia, 2015.
@inproceedings{ERK2015Klemen,
title = {The pose-invariant similarity index for face recognition},
author = {Klemen Grm and Simon Dobrišek and Vitomir Štruc},
year = {2015},
date = {2015-04-20},
booktitle = {Proceedings of the Electrotechnical and Computer Science Conference (ERK)},
address = {Portorož, Slovenia},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Vitomir Štruc; Janez Križaj; Simon Dobrišek
Modest face recognition Proceedings Article
V: Proceedings of the International Workshop on Biometrics and Forensics (IWBF), str. 1–6, IEEE, 2015.
@inproceedings{struc2015modest,
title = {Modest face recognition},
author = {Vitomir Štruc and Janez Križaj and Simon Dobrišek},
url = {https://lmi.fe.uni-lj.si/en/modestfacerecognition/},
year = {2015},
date = {2015-01-01},
urldate = {2015-01-01},
booktitle = {Proceedings of the International Workshop on Biometrics and Forensics (IWBF)},
pages = {1--6},
publisher = {IEEE},
abstract = {The facial imagery usually at the disposal for forensics investigations is commonly of a poor quality due to the unconstrained settings in which it was acquired. The captured faces are typically non-frontal, partially occluded and of a low resolution, which makes the recognition task extremely difficult. In this paper we try to address this problem by presenting a novel framework for face recognition that combines diverse features sets (Gabor features, local binary patterns, local phase quantization features and pixel intensities), probabilistic linear discriminant analysis (PLDA) and data fusion based on linear logistic regression. With the proposed framework a matching score for the given pair of probe and target images is produced by applying PLDA on each of the four feature sets independently - producing a (partial) matching score for each of the PLDA-based feature vectors - and then combining the partial matching results at the score level to generate a single matching score for recognition. We make two main contributions in the paper: i) we introduce a novel framework for face recognition that relies on probabilistic MOdels of Diverse fEature SeTs (MODEST) to facilitate the recognition process and ii) benchmark it against the existing state-of-the-art. We demonstrate the feasibility of our MODEST framework on the FRGCv2 and PaSC databases and present comparative results with the state-of-the-art recognition techniques, which demonstrate the efficacy of our framework.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The facial imagery usually at the disposal for forensics investigations is commonly of a poor quality due to the unconstrained settings in which it was acquired. The captured faces are typically non-frontal, partially occluded and of a low resolution, which makes the recognition task extremely difficult. In this paper we try to address this problem by presenting a novel framework for face recognition that combines diverse features sets (Gabor features, local binary patterns, local phase quantization features and pixel intensities), probabilistic linear discriminant analysis (PLDA) and data fusion based on linear logistic regression. With the proposed framework a matching score for the given pair of probe and target images is produced by applying PLDA on each of the four feature sets independently - producing a (partial) matching score for each of the PLDA-based feature vectors - and then combining the partial matching results at the score level to generate a single matching score for recognition. We make two main contributions in the paper: i) we introduce a novel framework for face recognition that relies on probabilistic MOdels of Diverse fEature SeTs (MODEST) to facilitate the recognition process and ii) benchmark it against the existing state-of-the-art. We demonstrate the feasibility of our MODEST framework on the FRGCv2 and PaSC databases and present comparative results with the state-of-the-art recognition techniques, which demonstrate the efficacy of our framework.
Ross Beveridge; Hao Zhang; Bruce A Draper; Patrick J Flynn; Zhenhua Feng; Patrik Huber; Josef Kittler; Zhiwu Huang; Shaoxin Li; Yan Li; Vitomir Štruc; Janez Križaj; others
Report on the FG 2015 video person recognition evaluation Proceedings Article
V: 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (IEEE FG), str. 1–8, IEEE 2015.
@inproceedings{beveridge2015report,
title = {Report on the FG 2015 video person recognition evaluation},
author = {Ross Beveridge and Hao Zhang and Bruce A Draper and Patrick J Flynn and Zhenhua Feng and Patrik Huber and Josef Kittler and Zhiwu Huang and Shaoxin Li and Yan Li and Vitomir Štruc and Janez Križaj and others},
url = {https://lmi.fe.uni-lj.si/en/reportonthefg2015videopersonrecognitionevaluation/},
year = {2015},
date = {2015-01-01},
urldate = {2015-01-01},
booktitle = {11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (IEEE FG)},
volume = {1},
pages = {1--8},
organization = {IEEE},
abstract = {This report presents results from the Video Person Recognition Evaluation held in conjunction with the 11th IEEE International Conference on Automatic Face and Gesture Recognition. Two experiments required algorithms to recognize people in videos from the Point-and-Shoot Face Recognition Challenge Problem (PaSC). The first consisted of videos from a tripod mounted high quality video camera. The second contained videos acquired from 5 different handheld video cameras. There were 1401 videos in each experiment of 265 subjects. The subjects, the scenes, and the actions carried out by the people are the same in both experiments. Five groups from around the world participated in the evaluation. The video handheld experiment was included in the International Joint Conference on Biometrics (IJCB) 2014 Handheld Video Face and Person Recognition Competition. The top verification rate from this evaluation is double that of the top performer in the IJCB competition. Analysis shows that the factor most effecting algorithm performance is the combination of location and action: where the video was acquired and what the person was doing.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
This report presents results from the Video Person Recognition Evaluation held in conjunction with the 11th IEEE International Conference on Automatic Face and Gesture Recognition. Two experiments required algorithms to recognize people in videos from the Point-and-Shoot Face Recognition Challenge Problem (PaSC). The first consisted of videos from a tripod mounted high quality video camera. The second contained videos acquired from 5 different handheld video cameras. There were 1401 videos in each experiment of 265 subjects. The subjects, the scenes, and the actions carried out by the people are the same in both experiments. Five groups from around the world participated in the evaluation. The video handheld experiment was included in the International Joint Conference on Biometrics (IJCB) 2014 Handheld Video Face and Person Recognition Competition. The top verification rate from this evaluation is double that of the top performer in the IJCB competition. Analysis shows that the factor most effecting algorithm performance is the combination of location and action: where the video was acquired and what the person was doing.
Tadej Justin; Vitomir Štruc; Simon Dobrišek; Boštjan Vesnicer; Ivo Ipšić; France Mihelič
Speaker de-identification using diphone recognition and speech synthesis Proceedings Article
V: 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (IEEE FG): DeID 2015, str. 1–7, IEEE 2015.
@inproceedings{justin2015speaker,
title = {Speaker de-identification using diphone recognition and speech synthesis},
author = {Tadej Justin and Vitomir Štruc and Simon Dobrišek and Boštjan Vesnicer and Ivo Ipšić and France Mihelič},
url = {https://lmi.fe.uni-lj.si/en/speakerde-identificationusingdiphonerecognitionandspeechsynthesis/},
year = {2015},
date = {2015-01-01},
urldate = {2015-01-01},
booktitle = {11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (IEEE FG): DeID 2015},
volume = {4},
pages = {1--7},
organization = {IEEE},
abstract = {The paper addresses the problem of speaker (or voice) de-identification by presenting a novel approach for concealing the identity of speakers in their speech. The proposed technique first recognizes the input speech with a diphone recognition system and then transforms the obtained phonetic transcription into the speech of another speaker with a speech synthesis system. Due to the fact that a Diphone RecOgnition step and a sPeech SYnthesis step are used during the deidentification, we refer to the developed technique as DROPSY. With this approach the acoustical models of the recognition and synthesis modules are completely independent from each other, which ensures the highest level of input speaker deidentification. The proposed DROPSY-based de-identification approach is language dependent, text independent and capable of running in real-time due to the relatively simple computing methods used. When designing speaker de-identification technology two requirements are typically imposed on the deidentification techniques: i) it should not be possible to establish the identity of the speakers based on the de-identified speech, and ii) the processed speech should still sound natural and be intelligible. This paper, therefore, implements the proposed DROPSY-based approach with two different speech synthesis techniques (i.e, with the HMM-based and the diphone TDPSOLA- based technique). The obtained de-identified speech is evaluated for intelligibility and evaluated in speaker verification experiments with a state-of-the-art (i-vector/PLDA) speaker recognition system. The comparison of both speech synthesis modules integrated in the proposed method reveals that both can efficiently de-identify the input speakers while still producing intelligible speech.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The paper addresses the problem of speaker (or voice) de-identification by presenting a novel approach for concealing the identity of speakers in their speech. The proposed technique first recognizes the input speech with a diphone recognition system and then transforms the obtained phonetic transcription into the speech of another speaker with a speech synthesis system. Due to the fact that a Diphone RecOgnition step and a sPeech SYnthesis step are used during the deidentification, we refer to the developed technique as DROPSY. With this approach the acoustical models of the recognition and synthesis modules are completely independent from each other, which ensures the highest level of input speaker deidentification. The proposed DROPSY-based de-identification approach is language dependent, text independent and capable of running in real-time due to the relatively simple computing methods used. When designing speaker de-identification technology two requirements are typically imposed on the deidentification techniques: i) it should not be possible to establish the identity of the speakers based on the de-identified speech, and ii) the processed speech should still sound natural and be intelligible. This paper, therefore, implements the proposed DROPSY-based approach with two different speech synthesis techniques (i.e, with the HMM-based and the diphone TDPSOLA- based technique). The obtained de-identified speech is evaluated for intelligibility and evaluated in speaker verification experiments with a state-of-the-art (i-vector/PLDA) speaker recognition system. The comparison of both speech synthesis modules integrated in the proposed method reveals that both can efficiently de-identify the input speakers while still producing intelligible speech.
Simon Dobrišek; Vitomir Štruc; Janez Križaj; France Mihelič
Face recognition in the wild with the Probabilistic Gabor-Fisher Classifier Proceedings Article
V: 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (IEEE FG): BWild 2015, str. 1–6, IEEE 2015.
@inproceedings{dobrivsek2015face,
title = {Face recognition in the wild with the Probabilistic Gabor-Fisher Classifier},
author = {Simon Dobrišek and Vitomir Štruc and Janez Križaj and France Mihelič},
url = {https://lmi.fe.uni-lj.si/en/facerecognitioninthewildwiththeprobabilisticgabor-fisherclassifier/},
year = {2015},
date = {2015-01-01},
urldate = {2015-01-01},
booktitle = {11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (IEEE FG): BWild 2015},
volume = {2},
pages = {1--6},
organization = {IEEE},
abstract = {The paper addresses the problem of face recognition in the wild. It introduces a novel approach to unconstrained face recognition that exploits Gabor magnitude features and a simplified version of the probabilistic linear discriminant analysis (PLDA). The novel approach, named Probabilistic Gabor-Fisher Classifier (PGFC), first extracts a vector of Gabor magnitude features from the given input image using a battery of Gabor filters, then reduces the dimensionality of the extracted feature vector by projecting it into a low-dimensional subspace and finally produces a representation suitable for identity inference by applying PLDA to the projected feature vector. The proposed approach extends the popular Gabor-Fisher Classifier (GFC) to a probabilistic setting and thus improves on the generalization capabilities of the GFC method. The PGFC technique is assessed in face verification experiments on the Point and Shoot Face Recognition Challenge (PaSC) database, which features real-world videos of subjects performing everyday tasks. Experimental results on this challenging database show the feasibility of the proposed approach, which improves on the best results on this database reported in the literature by the time of writing.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The paper addresses the problem of face recognition in the wild. It introduces a novel approach to unconstrained face recognition that exploits Gabor magnitude features and a simplified version of the probabilistic linear discriminant analysis (PLDA). The novel approach, named Probabilistic Gabor-Fisher Classifier (PGFC), first extracts a vector of Gabor magnitude features from the given input image using a battery of Gabor filters, then reduces the dimensionality of the extracted feature vector by projecting it into a low-dimensional subspace and finally produces a representation suitable for identity inference by applying PLDA to the projected feature vector. The proposed approach extends the popular Gabor-Fisher Classifier (GFC) to a probabilistic setting and thus improves on the generalization capabilities of the GFC method. The PGFC technique is assessed in face verification experiments on the Point and Shoot Face Recognition Challenge (PaSC) database, which features real-world videos of subjects performing everyday tasks. Experimental results on this challenging database show the feasibility of the proposed approach, which improves on the best results on this database reported in the literature by the time of writing.
Tadej Justin; Vitomir Štruc; Janez Žibert; France Mihelič
Development and Evaluation of the Emotional Slovenian Speech Database-EmoLUKS Proceedings Article
V: Proceedings of the International Conference on Text, Speech, and Dialogue (TSD), str. 351–359, Springer 2015.
@inproceedings{justin2015development,
title = {Development and Evaluation of the Emotional Slovenian Speech Database-EmoLUKS},
author = {Tadej Justin and Vitomir Štruc and Janez Žibert and France Mihelič},
url = {https://lmi.fe.uni-lj.si/en/developmentandevaluationoftheemotionalslovenianspeechdatabase-emoluks/},
year = {2015},
date = {2015-01-01},
urldate = {2015-01-01},
booktitle = {Proceedings of the International Conference on Text, Speech, and Dialogue (TSD)},
pages = {351--359},
organization = {Springer},
abstract = {This paper describes a speech database built from 17 Slovenian radio dramas. The dramas were obtained from the national radio-and-television station (RTV Slovenia) and were given at the universities disposal with an academic license for processing and annotating the audio material. The utterances of one male and one female speaker were transcribed, segmented and then annotated with emotional states of the speakers. The annotation of the emotional states was conducted in two stages with our own web-based application for crowd sourcing. The final (emotional) speech database consists of 1385 recordings of one male (975 recordings) and one female (410 recordings) speaker and contains labeled emotional speech with a total duration of around 1 hour and 15 minutes. The paper presents the two-stage annotation process used to label the data and demonstrates the usefulness of the employed annotation methodology. Baseline emotion recognition experiments are also presented. The reported results are presented with the un-weighted as well as weighted average recalls and precisions for 2-class and 7-class recognition experiments.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper describes a speech database built from 17 Slovenian radio dramas. The dramas were obtained from the national radio-and-television station (RTV Slovenia) and were given at the universities disposal with an academic license for processing and annotating the audio material. The utterances of one male and one female speaker were transcribed, segmented and then annotated with emotional states of the speakers. The annotation of the emotional states was conducted in two stages with our own web-based application for crowd sourcing. The final (emotional) speech database consists of 1385 recordings of one male (975 recordings) and one female (410 recordings) speaker and contains labeled emotional speech with a total duration of around 1 hour and 15 minutes. The paper presents the two-stage annotation process used to label the data and demonstrates the usefulness of the employed annotation methodology. Baseline emotion recognition experiments are also presented. The reported results are presented with the un-weighted as well as weighted average recalls and precisions for 2-class and 7-class recognition experiments.
Necati Cihan Camgoz; Vitomir Štruc; Berk Gokberk; Lale Akarun; Ahmet Alp Kindiroglu
Facial Landmark Localization in Depth Images using Supervised Ridge Descent Proceedings Article
V: Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCVW): Chaa Learn, str. 136–141, 2015.
@inproceedings{cihan2015facial,
title = {Facial Landmark Localization in Depth Images using Supervised Ridge Descent},
author = {Necati Cihan Camgoz and Vitomir Štruc and Berk Gokberk and Lale Akarun and Ahmet Alp Kindiroglu},
url = {https://lmi.fe.uni-lj.si/en/faciallandmarklocalizationindepthimagesusingsupervisedridgedescent/},
year = {2015},
date = {2015-01-01},
urldate = {2015-01-01},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCVW): Chaa Learn},
pages = {136--141},
abstract = {Supervised Descent Method (SDM) has proven successful in many computer vision applications such as face alignment, tracking and camera calibration. Recent studies which used SDM, achieved state of the-art performance on facial landmark localization in depth images [4]. In this study, we propose to use ridge regression instead of least squares regression for learning the SDM, and to change feature sizes in each iteration, effectively turning the landmark search into a coarse to fine process. We apply the proposed method to facial landmark localization on the Bosphorus 3D Face Database; using frontal depth images with no occlusion. Experimental results confirm that both ridge regression and using adaptive feature sizes improve the localization accuracy considerably},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Supervised Descent Method (SDM) has proven successful in many computer vision applications such as face alignment, tracking and camera calibration. Recent studies which used SDM, achieved state of the-art performance on facial landmark localization in depth images [4]. In this study, we propose to use ridge regression instead of least squares regression for learning the SDM, and to change feature sizes in each iteration, effectively turning the landmark search into a coarse to fine process. We apply the proposed method to facial landmark localization on the Bosphorus 3D Face Database; using frontal depth images with no occlusion. Experimental results confirm that both ridge regression and using adaptive feature sizes improve the localization accuracy considerably
2014
Journal Articles
Peter Peer; Žiga Emeršič; Jernej Bule; Jerneja Žganec-Gros; Vitomir Štruc
Strategies for exploiting independent cloud implementations of biometric experts in multibiometric scenarios Članek v strokovni reviji
V: Mathematical problems in engineering, vol. 2014, 2014.
@article{peer2014strategies,
title = {Strategies for exploiting independent cloud implementations of biometric experts in multibiometric scenarios},
author = {Peter Peer and Žiga Emeršič and Jernej Bule and Jerneja Žganec-Gros and Vitomir Štruc},
url = {https://lmi.fe.uni-lj.si/en/strategiesforexploitingindependentcloudimplementationsofbiometricexpertsinmultibiometricscenarios/},
doi = {http://dx.doi.org/10.1155/2014/585139},
year = {2014},
date = {2014-01-01},
urldate = {2014-01-01},
journal = {Mathematical problems in engineering},
volume = {2014},
publisher = {Hindawi Publishing Corporation},
abstract = {Cloud computing represents one of the fastest growing areas of technology and offers a new computing model for various applications and services. This model is particularly interesting for the area of biometric recognition, where scalability, processing power, and storage requirements are becoming a bigger and bigger issue with each new generation of recognition technology. Next to the availability of computing resources, another important aspect of cloud computing with respect to biometrics is accessibility. Since biometric cloud services are easily accessible, it is possible to combine different existing implementations and design new multibiometric services that next to almost unlimited resources also offer superior recognition performance and, consequently, ensure improved security to its client applications. Unfortunately, the literature on the best strategies of how to combine existing implementations of cloud-based biometric experts into a multibiometric service is virtually nonexistent. In this paper, we try to close this gap and evaluate different strategies for combining existing biometric experts into a multibiometric cloud service. We analyze the (fusion) strategies from different perspectives such as performance gains, training complexity, or resource consumption and present results and findings important to software developers and other researchers working in the areas of biometrics and cloud computing. The analysis is conducted based on two biometric cloud services, which are also presented in the paper.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Cloud computing represents one of the fastest growing areas of technology and offers a new computing model for various applications and services. This model is particularly interesting for the area of biometric recognition, where scalability, processing power, and storage requirements are becoming a bigger and bigger issue with each new generation of recognition technology. Next to the availability of computing resources, another important aspect of cloud computing with respect to biometrics is accessibility. Since biometric cloud services are easily accessible, it is possible to combine different existing implementations and design new multibiometric services that next to almost unlimited resources also offer superior recognition performance and, consequently, ensure improved security to its client applications. Unfortunately, the literature on the best strategies of how to combine existing implementations of cloud-based biometric experts into a multibiometric service is virtually nonexistent. In this paper, we try to close this gap and evaluate different strategies for combining existing biometric experts into a multibiometric cloud service. We analyze the (fusion) strategies from different perspectives such as performance gains, training complexity, or resource consumption and present results and findings important to software developers and other researchers working in the areas of biometrics and cloud computing. The analysis is conducted based on two biometric cloud services, which are also presented in the paper.
Vitomir Štruc; Jerneja Žganec-Gros; Boštjan Vesnicer; Nikola Pavešić
Beyond parametric score normalisation in biometric verification systems Članek v strokovni reviji
V: IET Biometrics, vol. 3, no. 2, str. 62–74, 2014.
@article{struc2014beyond,
title = {Beyond parametric score normalisation in biometric verification systems},
author = {Vitomir Štruc and Jerneja Žganec-Gros and Boštjan Vesnicer and Nikola Pavešić},
url = {https://lmi.fe.uni-lj.si/en/beyondparametricscorenormalisationinbiometricverificationsystems/},
doi = {10.1049/iet-bmt.2013.0076},
year = {2014},
date = {2014-01-01},
urldate = {2014-01-01},
journal = {IET Biometrics},
volume = {3},
number = {2},
pages = {62--74},
publisher = {IET},
abstract = {Similarity scores represent the basis for identity inference in biometric verification systems. However, because of the so-called miss-matched conditions across enrollment and probe samples and identity-dependent factors these scores typically exhibit statistical variations that affect the verification performance of biometric systems. To mitigate these variations, scorenormalisation techniques, such as the z-norm, the t-norm or the zt-norm, are commonly adopted. In this study, the authors study the problem of score normalisation in the scope of biometric verification and introduce a new class of non-parametric normalisation techniques, which make no assumptions regarding the shape of the distribution from which the scores are drawn (as the parametric techniques do). Instead, they estimate the shape of the score distribution and use the estimate to map the initial distribution to a common (predefined) distribution. Based on the new class of normalisation techniques they also develop a hybrid normalisation scheme that combines non-parametric and parametric techniques into hybrid two-step procedures. They evaluate the performance of the non-parametric and hybrid techniques in face-verification experiments on the FRGCv2 and SCFace databases and show that the non-parametric techniques outperform their parametric counterparts and that the hybrid procedure is not only feasible, but also retains some desirable characteristics from both the non-parametric and the parametric techniques.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Similarity scores represent the basis for identity inference in biometric verification systems. However, because of the so-called miss-matched conditions across enrollment and probe samples and identity-dependent factors these scores typically exhibit statistical variations that affect the verification performance of biometric systems. To mitigate these variations, scorenormalisation techniques, such as the z-norm, the t-norm or the zt-norm, are commonly adopted. In this study, the authors study the problem of score normalisation in the scope of biometric verification and introduce a new class of non-parametric normalisation techniques, which make no assumptions regarding the shape of the distribution from which the scores are drawn (as the parametric techniques do). Instead, they estimate the shape of the score distribution and use the estimate to map the initial distribution to a common (predefined) distribution. Based on the new class of normalisation techniques they also develop a hybrid normalisation scheme that combines non-parametric and parametric techniques into hybrid two-step procedures. They evaluate the performance of the non-parametric and hybrid techniques in face-verification experiments on the FRGCv2 and SCFace databases and show that the non-parametric techniques outperform their parametric counterparts and that the hybrid procedure is not only feasible, but also retains some desirable characteristics from both the non-parametric and the parametric techniques.
Žiga Emeršič; Jernej Bule; Jerneja Žganec-Gros; Vitomir Štruc; Peter Peer
A case study on multi-modal biometrics in the cloud Članek v strokovni reviji
V: Electrotechnical Review, vol. 81, no. 3, str. 74, 2014.
@article{emersic2014case,
title = {A case study on multi-modal biometrics in the cloud},
author = {Žiga Emeršič and Jernej Bule and Jerneja Žganec-Gros and Vitomir Štruc and Peter Peer},
url = {https://lmi.fe.uni-lj.si/en/acasestudyonmulti-modalbiometricsinthecloud/},
year = {2014},
date = {2014-01-01},
urldate = {2014-01-01},
journal = {Electrotechnical Review},
volume = {81},
number = {3},
pages = {74},
publisher = {Elektrotehniski Vestnik},
abstract = {Cloud computing is particularly interesting for the area of biometric recognition, where scalability, availability and accessibility are important aspects. In this paper we try to evaluate different strategies for combining existing uni-modal (cloud-based) biometric experts into a multi-biometric cloud-service. We analyze several fusion strategies from the perspective of performance gains, training complexity and resource consumption and discuss the results of our analysis. The experimental evaluation is conducted based on two biometric cloud-services developed in the scope of the Competence Centere CLASS, a face recognition service and a fingerprint recognition service, which are also briefly described in the paper. The presented results are important to researchers and developers working in the area of biometric services for the cloud looking for easy solutions for improving the quality of their services.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Cloud computing is particularly interesting for the area of biometric recognition, where scalability, availability and accessibility are important aspects. In this paper we try to evaluate different strategies for combining existing uni-modal (cloud-based) biometric experts into a multi-biometric cloud-service. We analyze several fusion strategies from the perspective of performance gains, training complexity and resource consumption and discuss the results of our analysis. The experimental evaluation is conducted based on two biometric cloud-services developed in the scope of the Competence Centere CLASS, a face recognition service and a fingerprint recognition service, which are also briefly described in the paper. The presented results are important to researchers and developers working in the area of biometric services for the cloud looking for easy solutions for improving the quality of their services.
Proceedings Articles
Janez Križaj; Vitomir Štruc; France Mihelič
A Feasibility Study on the Use of Binary Keypoint Descriptors for 3D Face Recognition Proceedings Article
V: Proceedings of the Mexican Conference on Pattern Recognition (MCPR), str. 142–151, Springer 2014.
@inproceedings{krivzaj2014feasibility,
title = {A Feasibility Study on the Use of Binary Keypoint Descriptors for 3D Face Recognition},
author = {Janez Križaj and Vitomir Štruc and France Mihelič},
url = {https://lmi.fe.uni-lj.si/en/afeasibilitystudyontheuseofbinarykeypointdescriptorsfor3dfacerecognition/},
year = {2014},
date = {2014-01-01},
urldate = {2014-01-01},
booktitle = {Proceedings of the Mexican Conference on Pattern Recognition (MCPR)},
pages = {142--151},
organization = {Springer},
abstract = {Despite the progress made in the area of local image descriptors in recent years, virtually no literature is available on the use of more recent descriptors for the problem of 3D face recognition, such as BRIEF, ORB, BRISK or FREAK, which are binary in nature and, therefore, tend to be faster to compute and match, while requiring signi cantly less memory for storage than, for example, SIFT or SURF. In this paper, we try to close this gap and present a feasibility study on the use of these descriptors for 3D face recognition. Descriptors are evaluated on the three challenging 3D face image datasets, namely, the FRGC, UMB and CASIA. Our experiments show the binary descriptors ensure slightly lower veri cation rates than SIFT, comparable to those of the SURF descriptor, while being an order of magnitude faster than SIFT. The results suggest that the use of binary descriptors represents a viable alternative to the established descriptors.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Despite the progress made in the area of local image descriptors in recent years, virtually no literature is available on the use of more recent descriptors for the problem of 3D face recognition, such as BRIEF, ORB, BRISK or FREAK, which are binary in nature and, therefore, tend to be faster to compute and match, while requiring signi cantly less memory for storage than, for example, SIFT or SURF. In this paper, we try to close this gap and present a feasibility study on the use of these descriptors for 3D face recognition. Descriptors are evaluated on the three challenging 3D face image datasets, namely, the FRGC, UMB and CASIA. Our experiments show the binary descriptors ensure slightly lower veri cation rates than SIFT, comparable to those of the SURF descriptor, while being an order of magnitude faster than SIFT. The results suggest that the use of binary descriptors represents a viable alternative to the established descriptors.
Janez Križaj; Vitomir Štruc; Simon Dobrišek; Darijan Marčetić; Slobodan Ribarić
SIFT vs. FREAK: Assessing the usefulness of two keypoint descriptors for 3D face verification Proceedings Article
V: 37th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), str. 1336–1341, Mipro Opatija, Croatia, 2014.
@inproceedings{krivzaj2014sift,
title = {SIFT vs. FREAK: Assessing the usefulness of two keypoint descriptors for 3D face verification},
author = {Janez Križaj and Vitomir Štruc and Simon Dobrišek and Darijan Marčetić and Slobodan Ribarić},
url = {https://lmi.fe.uni-lj.si/en/siftvs-freakassessingtheusefulnessoftwokeypointdescriptorsfor3dfaceverification/},
year = {2014},
date = {2014-01-01},
urldate = {2014-01-01},
booktitle = {37th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO)},
pages = {1336--1341},
address = {Opatija, Croatia},
organization = {Mipro},
abstract = {Many techniques in the area of 3D face recognition rely on local descriptors to characterize the surface-shape information around points of interest (or keypoints) in the 3D images. Despite the fact that a lot of advancements have been made in the area of keypoint descriptors over the last years, the literature on 3D-face recognition for the most part still focuses on established descriptors, such as SIFT and SURF, and largely neglects more recent descriptors, such as the FREAK descriptor. In this paper we try to bridge this gap and assess the usefulness of the FREAK descriptor for the task for 3D face recognition. Of particular interest to us is a direct comparison of the FREAK and SIFT descriptors within a simple verification framework. To evaluate our framework with the two descriptors, we conduct 3D face recognition experiments on the challenging FRGCv2 and UMBDB databases and show that the FREAK descriptor ensures a very competitive verification performance when compared to the SIFT descriptor, but at a fraction of the computational cost. Our results indicate that the FREAK descriptor is a viable alternative to the SIFT descriptor for the problem of 3D face verification and due to its binary nature is particularly useful for real-time recognition systems and verification techniques for low-resource devices such as mobile phones, tablets and alike.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Many techniques in the area of 3D face recognition rely on local descriptors to characterize the surface-shape information around points of interest (or keypoints) in the 3D images. Despite the fact that a lot of advancements have been made in the area of keypoint descriptors over the last years, the literature on 3D-face recognition for the most part still focuses on established descriptors, such as SIFT and SURF, and largely neglects more recent descriptors, such as the FREAK descriptor. In this paper we try to bridge this gap and assess the usefulness of the FREAK descriptor for the task for 3D face recognition. Of particular interest to us is a direct comparison of the FREAK and SIFT descriptors within a simple verification framework. To evaluate our framework with the two descriptors, we conduct 3D face recognition experiments on the challenging FRGCv2 and UMBDB databases and show that the FREAK descriptor ensures a very competitive verification performance when compared to the SIFT descriptor, but at a fraction of the computational cost. Our results indicate that the FREAK descriptor is a viable alternative to the SIFT descriptor for the problem of 3D face verification and due to its binary nature is particularly useful for real-time recognition systems and verification techniques for low-resource devices such as mobile phones, tablets and alike.
Darijan Marčetić; Slobodan Ribarić; Vitomir Štruc; Nikola Pavešić
An experimental tattoo de-identification system for privacy protection in still images Proceedings Article
V: 37th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), str. 1288–1293, Mipro IEEE, 2014.
@inproceedings{marcetic2014experimental,
title = {An experimental tattoo de-identification system for privacy protection in still images},
author = {Darijan Marčetić and Slobodan Ribarić and Vitomir Štruc and Nikola Pavešić},
url = {https://lmi.fe.uni-lj.si/en/anexperimentaltattoode-identificationsystemforprivacyprotectioninstillimages/},
year = {2014},
date = {2014-01-01},
urldate = {2014-01-01},
booktitle = {37th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO)},
pages = {1288--1293},
publisher = {IEEE},
organization = {Mipro},
abstract = {An experimental tattoo de-identification system for privacy protection in still images is described in the paper. The system consists of the following modules: skin detection, region of interest detection, feature extraction, tattoo database, matching, tattoo detection, skin swapping, and quality evaluation. Two methods for tattoo localization are presented. The first is a simple ad-hoc method based only on skin colour. The second is based on skin colour, texture and SIFT features. The appearance of each tattoo area is de-identified in such a way that its skin colour and skin texture are similar to the surrounding skin area. Experimental results for still images in which tattoo location, distance, size, illumination, and motion blur have large variability are presented. The system is subjectively evaluated based on the results of tattoo localization, the level of privacy protection and the naturalness of the de-identified still images. The level of privacy protection is estimated based on the quality of the removal of the tattoo appearance and the concealment of its location.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
An experimental tattoo de-identification system for privacy protection in still images is described in the paper. The system consists of the following modules: skin detection, region of interest detection, feature extraction, tattoo database, matching, tattoo detection, skin swapping, and quality evaluation. Two methods for tattoo localization are presented. The first is a simple ad-hoc method based only on skin colour. The second is based on skin colour, texture and SIFT features. The appearance of each tattoo area is de-identified in such a way that its skin colour and skin texture are similar to the surrounding skin area. Experimental results for still images in which tattoo location, distance, size, illumination, and motion blur have large variability are presented. The system is subjectively evaluated based on the results of tattoo localization, the level of privacy protection and the naturalness of the de-identified still images. The level of privacy protection is estimated based on the quality of the removal of the tattoo appearance and the concealment of its location.
Boštjan Vesnicer; Jerneja Žganec-Gros; Simon Dobrišek; Vitomir Štruc
Incorporating Duration Information into I-Vector-Based Speaker-Recognition Systems Proceedings Article
V: Proceedings of Odyssey: The Speaker and Language Recognition Workshop, str. 241–248, 2014.
@inproceedings{vesnicer2014incorporating,
title = {Incorporating Duration Information into I-Vector-Based Speaker-Recognition Systems},
author = {Boštjan Vesnicer and Jerneja Žganec-Gros and Simon Dobrišek and Vitomir Štruc},
url = {https://lmi.fe.uni-lj.si/en/incorporatingdurationinformationintoi-vector-basedspeaker-recognitionsystems/},
year = {2014},
date = {2014-01-01},
urldate = {2014-01-01},
booktitle = {Proceedings of Odyssey: The Speaker and Language Recognition Workshop},
pages = {241--248},
abstract = {Most of the existing literature on i-vector-based speaker recognition focuses on recognition problems, where i-vectors are extracted from speech recordings of sufficient length. The majority of modeling/recognition techniques therefore simply ignores the fact that the i-vectors are most likely estimated unreliably when short recordings are used for their computation. Only recently, were a number of solutions proposed in the literature to address the problem of duration variability, all treating the i-vector as a random variable whose posterior distribution can be parameterized by the posterior mean and the posterior covariance. In this setting the covariance matrix serves as a measure of uncertainty that is related to the length of the available recording. In contract to these solutions, we address the problem of duration variability through weighted statistics. We demonstrate in the paper how established feature transformation techniques regularly used in the area of speaker recognition, such as PCA or WCCN, can be modified to take duration into account. We evaluate our weighting scheme in the scope of the i-vector challenge organized as part of the Odyssey, Speaker and Language Recognition Workshop 2014 and achieve a minimal DCF of 0.280, which at the time of writing puts our approach in third place among all the participating institutions.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Most of the existing literature on i-vector-based speaker recognition focuses on recognition problems, where i-vectors are extracted from speech recordings of sufficient length. The majority of modeling/recognition techniques therefore simply ignores the fact that the i-vectors are most likely estimated unreliably when short recordings are used for their computation. Only recently, were a number of solutions proposed in the literature to address the problem of duration variability, all treating the i-vector as a random variable whose posterior distribution can be parameterized by the posterior mean and the posterior covariance. In this setting the covariance matrix serves as a measure of uncertainty that is related to the length of the available recording. In contract to these solutions, we address the problem of duration variability through weighted statistics. We demonstrate in the paper how established feature transformation techniques regularly used in the area of speaker recognition, such as PCA or WCCN, can be modified to take duration into account. We evaluate our weighting scheme in the scope of the i-vector challenge organized as part of the Odyssey, Speaker and Language Recognition Workshop 2014 and achieve a minimal DCF of 0.280, which at the time of writing puts our approach in third place among all the participating institutions.
Ross Beveridge; Hao Zhang; Patrick Flynn; Yooyoung Lee; Venice Erin Liong; Jiwen Lu; Marcus Assis de Angeloni; Tiago Freitas de Pereira; Haoxiang Li; Gang Hua; Vitomir Štruc; Janez Križaj; Jonathon Phillips
The ijcb 2014 pasc video face and person recognition competition Proceedings Article
V: Proceedings of the IEEE International Joint Conference on Biometrics (IJCB), str. 1–8, IEEE 2014.
@inproceedings{beveridge2014ijcb,
title = {The ijcb 2014 pasc video face and person recognition competition},
author = {Ross Beveridge and Hao Zhang and Patrick Flynn and Yooyoung Lee and Venice Erin Liong and Jiwen Lu and Marcus Assis de Angeloni and Tiago Freitas de Pereira and Haoxiang Li and Gang Hua and Vitomir Štruc and Janez Križaj and Jonathon Phillips},
url = {https://lmi.fe.uni-lj.si/en/theijcb2014pascvideofaceandpersonrecognitioncompetition/},
year = {2014},
date = {2014-01-01},
urldate = {2014-01-01},
booktitle = {Proceedings of the IEEE International Joint Conference on Biometrics (IJCB)},
pages = {1--8},
organization = {IEEE},
abstract = {The Point-and-Shoot Face Recognition Challenge (PaSC) is a performance evaluation challenge including 1401 videos of 265 people acquired with handheld cameras and depicting people engaged in activities with non-frontal head pose. This report summarizes the results from a competition using this challenge problem. In the Video-to-video Experiment a person in a query video is recognized by comparing the query video to a set of target videos. Both target and query videos are drawn from the same pool of 1401 videos. In the Still-to-video Experiment the person in a query video is to be recognized by comparing the query video to a larger target set consisting of still images. Algorithm performance is characterized by verification rate at a false accept rate of 0:01 and associated receiver operating characteristic (ROC) curves. Participants were provided eye coordinates for video frames. Results were submitted by 4 institutions: (i) Advanced Digital Science Center, Singapore; (ii) CPqD, Brasil; (iii) Stevens Institute of Technology, USA; and (iv) University of Ljubljana, Slovenia. Most competitors demonstrated video face recognition performance superior to the baseline provided with PaSC. The results represent the best performance to date on the handheld video portion of the PaSC.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The Point-and-Shoot Face Recognition Challenge (PaSC) is a performance evaluation challenge including 1401 videos of 265 people acquired with handheld cameras and depicting people engaged in activities with non-frontal head pose. This report summarizes the results from a competition using this challenge problem. In the Video-to-video Experiment a person in a query video is recognized by comparing the query video to a set of target videos. Both target and query videos are drawn from the same pool of 1401 videos. In the Still-to-video Experiment the person in a query video is to be recognized by comparing the query video to a larger target set consisting of still images. Algorithm performance is characterized by verification rate at a false accept rate of 0:01 and associated receiver operating characteristic (ROC) curves. Participants were provided eye coordinates for video frames. Results were submitted by 4 institutions: (i) Advanced Digital Science Center, Singapore; (ii) CPqD, Brasil; (iii) Stevens Institute of Technology, USA; and (iv) University of Ljubljana, Slovenia. Most competitors demonstrated video face recognition performance superior to the baseline provided with PaSC. The results represent the best performance to date on the handheld video portion of the PaSC.
2013
Journal Articles
Vitomir Štruc; Jerneja Žganec-Gros; Nikola Pavešić; Simon Dobrišek
Zlivanje informacij za zanseljivo in robustno razpoznavanje obrazov Članek v strokovni reviji
V: Electrotechnical Review, vol. 80, no. 3, str. 1-12, 2013.
@article{EV_Struc_2013,
title = {Zlivanje informacij za zanseljivo in robustno razpoznavanje obrazov},
author = {Vitomir Štruc and Jerneja Žganec-Gros and Nikola Pavešić and Simon Dobrišek},
url = {https://lmi.fe.uni-lj.si/en/zlivanjeinformacijzazanseljivoinrobustnorazpoznavanjeobrazov/},
year = {2013},
date = {2013-09-01},
urldate = {2013-09-01},
journal = {Electrotechnical Review},
volume = {80},
number = {3},
pages = {1-12},
abstract = {The existing face recognition technology has reached a performance level where it is possible to deploy it in various applications providing they are capable of ensuring controlled conditions for the image acquisition procedure. However, the technology still struggles with its recognition performance when deployed in uncontrolled and unconstrained conditions. In this paper, we present a novel approach to face recognition designed specifically for these challenging conditions. The proposed approach exploits information fusion to achieve robustness. In the first step, the approach crops the facial region from each input image in three different ways. It then maps each of the three crops into one of four color representations and finally extracts several feature types from each of the twelve facial representations. The described procedure results in a total of thirty facial representations that are combined at the matching score level using a fusion approach based on linear logistic regression (LLR) to arrive at a robust decision regarding the identity of the subject depicted in the input face image. The presented approach was enlisted as a representative of the University of Ljubljana and Alpineon d.o.o. to the 2013 face-recognition competition that was held in conjunction with the IAPR International Conference on Biometrics and achieved the best overall recognition results among all competition participants. Here, we describe the basic characteristics of the approach, elaborate on the results of the competition and, most importantly, present some interesting findings made during our development work that are also of relevance to the research community working in the field of face recognition.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The existing face recognition technology has reached a performance level where it is possible to deploy it in various applications providing they are capable of ensuring controlled conditions for the image acquisition procedure. However, the technology still struggles with its recognition performance when deployed in uncontrolled and unconstrained conditions. In this paper, we present a novel approach to face recognition designed specifically for these challenging conditions. The proposed approach exploits information fusion to achieve robustness. In the first step, the approach crops the facial region from each input image in three different ways. It then maps each of the three crops into one of four color representations and finally extracts several feature types from each of the twelve facial representations. The described procedure results in a total of thirty facial representations that are combined at the matching score level using a fusion approach based on linear logistic regression (LLR) to arrive at a robust decision regarding the identity of the subject depicted in the input face image. The presented approach was enlisted as a representative of the University of Ljubljana and Alpineon d.o.o. to the 2013 face-recognition competition that was held in conjunction with the IAPR International Conference on Biometrics and achieved the best overall recognition results among all competition participants. Here, we describe the basic characteristics of the approach, elaborate on the results of the competition and, most importantly, present some interesting findings made during our development work that are also of relevance to the research community working in the field of face recognition.
Simon Dobrišek; Rok Gajšek; France Mihelič; Nikola Pavešić; Vitomir Štruc
Towards efficient multi-modal emotion recognition Članek v strokovni reviji
V: International Journal of Advanced Robotic Systems, vol. 10, no. 53, 2013.
@article{dobrivsek2013towards,
title = {Towards efficient multi-modal emotion recognition},
author = {Simon Dobrišek and Rok Gajšek and France Mihelič and Nikola Pavešić and Vitomir Štruc},
url = {https://lmi.fe.uni-lj.si/en/towardsefficientmulti-modalemotionrecognition/},
doi = {10.5772/54002},
year = {2013},
date = {2013-01-01},
urldate = {2013-01-01},
journal = {International Journal of Advanced Robotic Systems},
volume = {10},
number = {53},
abstract = {The paper presents a multi-modal emotion recognition system exploiting audio and video (i.e., facial expression) information. The system first processes both sources of information individually to produce corresponding matching scores and then combines the computed matching scores to obtain a classification decision. For the video part of the system, a novel approach to emotion recognition, relying on image-set matching, is developed. The proposed approach avoids the need for detecting and tracking specific facial landmarks throughout the given video sequence, which represents a common source of error in video-based emotion recognition systems, and, therefore, adds robustness to the video processing chain. The audio part of the system, on the other hand, relies on utterance-specific Gaussian Mixture Models (GMMs) adapted from a Universal Background Model (UBM) via the maximum a posteriori probability (MAP) estimation. It improves upon the standard UBM-MAP procedure by exploiting gender information when building the utterance-specific GMMs, thus ensuring enhanced emotion recognition performance. Both the uni-modal parts as well as the combined system are assessed on the challenging multi-modal eNTERFACE'05 corpus with highly encouraging results. The developed system represents a feasible solution to emotion recognition that can easily be integrated into various systems, such as humanoid robots, smart surveillance systems and alike.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The paper presents a multi-modal emotion recognition system exploiting audio and video (i.e., facial expression) information. The system first processes both sources of information individually to produce corresponding matching scores and then combines the computed matching scores to obtain a classification decision. For the video part of the system, a novel approach to emotion recognition, relying on image-set matching, is developed. The proposed approach avoids the need for detecting and tracking specific facial landmarks throughout the given video sequence, which represents a common source of error in video-based emotion recognition systems, and, therefore, adds robustness to the video processing chain. The audio part of the system, on the other hand, relies on utterance-specific Gaussian Mixture Models (GMMs) adapted from a Universal Background Model (UBM) via the maximum a posteriori probability (MAP) estimation. It improves upon the standard UBM-MAP procedure by exploiting gender information when building the utterance-specific GMMs, thus ensuring enhanced emotion recognition performance. Both the uni-modal parts as well as the combined system are assessed on the challenging multi-modal eNTERFACE'05 corpus with highly encouraging results. The developed system represents a feasible solution to emotion recognition that can easily be integrated into various systems, such as humanoid robots, smart surveillance systems and alike.
Peter Peer; Jernej Bule; Jerneja Žganec Gros; Vitomir Štruc
Building cloud-based biometric services Članek v strokovni reviji
V: Informatica, vol. 37, no. 2, str. 115, 2013.
@article{peer2013building,
title = {Building cloud-based biometric services},
author = {Peter Peer and Jernej Bule and Jerneja Žganec Gros and Vitomir Štruc},
url = {https://lmi.fe.uni-lj.si/en/buildingcloud-basedbiometricservices/},
year = {2013},
date = {2013-01-01},
urldate = {2013-01-01},
journal = {Informatica},
volume = {37},
number = {2},
pages = {115},
publisher = {Slovenian Society Informatika/Slovensko drustvo Informatika},
abstract = {Over the next few years the amount of biometric data being at the disposal of various agencies and authentication service providers is expected to grow significantly. Such quantities of data require not only enormous amounts of storage but unprecedented processing power as well. To be able to face this future challenges more and more people are looking towards cloud computing, which can address these challenges quite effectively with its seemingly unlimited storage capacity, rapid data distribution and parallel processing capabilities. Since the available literature on how to implement cloud-based biometric services is extremely scarce, this paper capitalizes on the most important challenges encountered during the development work on biometric services, presents the most important standards and recommendations pertaining to biometric services in the cloud and ultimately, elaborates on the potential value of cloud-based biometric solutions by presenting a few existing (commercial) examples. In the final part of the paper, a case study on fingerprint recognition in the cloud and its integration into the e-learning environment Moodle is presented.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Over the next few years the amount of biometric data being at the disposal of various agencies and authentication service providers is expected to grow significantly. Such quantities of data require not only enormous amounts of storage but unprecedented processing power as well. To be able to face this future challenges more and more people are looking towards cloud computing, which can address these challenges quite effectively with its seemingly unlimited storage capacity, rapid data distribution and parallel processing capabilities. Since the available literature on how to implement cloud-based biometric services is extremely scarce, this paper capitalizes on the most important challenges encountered during the development work on biometric services, presents the most important standards and recommendations pertaining to biometric services in the cloud and ultimately, elaborates on the potential value of cloud-based biometric solutions by presenting a few existing (commercial) examples. In the final part of the paper, a case study on fingerprint recognition in the cloud and its integration into the e-learning environment Moodle is presented.
Vildana Sulič Kenk; Janez Križaj; Vitomir Štruc; Simon Dobrišek
Smart surveillance technologies in border control Članek v strokovni reviji
V: European Journal of Law and Technology, vol. 4, no. 2, 2013.
@article{kenk2013smart,
title = {Smart surveillance technologies in border control},
author = {Vildana Sulič Kenk and Janez Križaj and Vitomir Štruc and Simon Dobrišek},
url = {https://lmi.fe.uni-lj.si/en/smartsurveillancetechnologiesinbordercontrol/},
year = {2013},
date = {2013-01-01},
urldate = {2013-01-01},
journal = {European Journal of Law and Technology},
volume = {4},
number = {2},
abstract = {The paper addresses the technical and legal aspects of the existing and forthcoming intelligent ('smart') surveillance technologies that are (or are considered to be) employed in the border control application area. Such technologies provide a computerized decision-making support to border control authorities, and are intended to increase the reliability and efficiency of border control measures. However, the question that arises is how effective these technologies are, as well as at what price, economically, socially, and in terms of citizens' rights. The paper provides a brief overview of smart surveillance technologies in border control applications, especially those used for controlling cross-border traffic, discusses possible proportionality issues and privacy risks raised by the increasingly widespread use of such technologies, as well as good/best practises developed in this area. In a broader context, the paper presents the result of the research carried out as part of the SMART (Scalable Measures for Automated Recognition Technologies) project.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The paper addresses the technical and legal aspects of the existing and forthcoming intelligent ('smart') surveillance technologies that are (or are considered to be) employed in the border control application area. Such technologies provide a computerized decision-making support to border control authorities, and are intended to increase the reliability and efficiency of border control measures. However, the question that arises is how effective these technologies are, as well as at what price, economically, socially, and in terms of citizens' rights. The paper provides a brief overview of smart surveillance technologies in border control applications, especially those used for controlling cross-border traffic, discusses possible proportionality issues and privacy risks raised by the increasingly widespread use of such technologies, as well as good/best practises developed in this area. In a broader context, the paper presents the result of the research carried out as part of the SMART (Scalable Measures for Automated Recognition Technologies) project.
Blaz Stres; Woo Jun Sul; Bostjan Murovec; James M Tiedje
Recently Deglaciated High-Altitude Soils of the Himalaya: Diverse Environments, Heterogenous Bacterial Communities and Long-Range Dust Inputs from the Upper Troposphere Članek v strokovni reviji
V: PLOS ONE, vol. 8, no. 9, str. 1-10, 2013.
@article{10.1371/journal.pone.0076440,
title = {Recently Deglaciated High-Altitude Soils of the Himalaya: Diverse Environments, Heterogenous Bacterial Communities and Long-Range Dust Inputs from the Upper Troposphere},
author = {Blaz Stres and Woo Jun Sul and Bostjan Murovec and James M Tiedje},
url = {https://doi.org/10.1371/journal.pone.0076440},
doi = {10.1371/journal.pone.0076440},
year = {2013},
date = {2013-01-01},
journal = {PLOS ONE},
volume = {8},
number = {9},
pages = {1-10},
publisher = {Public Library of Science},
abstract = {Background The Himalaya with its altitude and geographical position forms a barrier to atmospheric transport, which produces much aqueous-particle monsoon precipitation and makes it the largest continuous ice-covered area outside polar regions. There is a paucity of data on high-altitude microbial communities, their native environments and responses to environmental-spatial variables relative to seasonal and deglaciation events. Methodology/Principal Findings Soils were sampled along altitude transects from 5000 m to 6000 m to determine environmental, spatial and seasonal factors structuring bacterial communities characterized by 16 S rRNA gene deep sequencing. Dust traps and fresh-snow samples were used to assess dust abundance and viability, community structure and abundance of dust associated microbial communities. Significantly different habitats among the altitude-transect samples corresponded to both phylogenetically distant and closely-related communities at distances as short as 50 m showing high community spatial divergence. High within-group variability that was related to an order of magnitude higher dust deposition obscured seasonal and temporal rearrangements in microbial communities. Although dust particle and associated cell deposition rates were highly correlated, seasonal dust communities of bacteria were distinct and differed significantly from recipient soil communities. Analysis of closest relatives to dust OTUs, HYSPLIT back-calculation of airmass trajectories and small dust particle size (4–12 µm) suggested that the deposited dust and microbes came from distant continental, lacustrine and marine sources, e.g. Sahara, India, Caspian Sea and Tibetan plateau. Cyanobacteria represented less than 0.5% of microbial communities suggesting that the microbial communities benefitted from (co)deposited carbon which was reflected in the psychrotolerant nature of dust-particle associated bacteria. Conclusions/Significance The spatial, environmental and temporal complexity of the high-altitude soils of the Himalaya generates ongoing disturbance and colonization events that subject heterogeneous microniches to stochastic colonization by far away dust associated microbes and result in the observed spatially divergent bacterial communities.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Background The Himalaya with its altitude and geographical position forms a barrier to atmospheric transport, which produces much aqueous-particle monsoon precipitation and makes it the largest continuous ice-covered area outside polar regions. There is a paucity of data on high-altitude microbial communities, their native environments and responses to environmental-spatial variables relative to seasonal and deglaciation events. Methodology/Principal Findings Soils were sampled along altitude transects from 5000 m to 6000 m to determine environmental, spatial and seasonal factors structuring bacterial communities characterized by 16 S rRNA gene deep sequencing. Dust traps and fresh-snow samples were used to assess dust abundance and viability, community structure and abundance of dust associated microbial communities. Significantly different habitats among the altitude-transect samples corresponded to both phylogenetically distant and closely-related communities at distances as short as 50 m showing high community spatial divergence. High within-group variability that was related to an order of magnitude higher dust deposition obscured seasonal and temporal rearrangements in microbial communities. Although dust particle and associated cell deposition rates were highly correlated, seasonal dust communities of bacteria were distinct and differed significantly from recipient soil communities. Analysis of closest relatives to dust OTUs, HYSPLIT back-calculation of airmass trajectories and small dust particle size (4–12 µm) suggested that the deposited dust and microbes came from distant continental, lacustrine and marine sources, e.g. Sahara, India, Caspian Sea and Tibetan plateau. Cyanobacteria represented less than 0.5% of microbial communities suggesting that the microbial communities benefitted from (co)deposited carbon which was reflected in the psychrotolerant nature of dust-particle associated bacteria. Conclusions/Significance The spatial, environmental and temporal complexity of the high-altitude soils of the Himalaya generates ongoing disturbance and colonization events that subject heterogeneous microniches to stochastic colonization by far away dust associated microbes and result in the observed spatially divergent bacterial communities.
Boštjan Murovec; Janez Perš; Rok Mandeljc; Vildana Sulić Kenk; Stanislav Kovačič
Towards commoditized smart-camera design Članek v strokovni reviji
V: Journal of Systems Architecture, vol. 59, no. 10, Part A, str. 847 - 858, 2013, ISSN: 1383-7621, (Smart Camera Architecture).
@article{MUROVEC2013847,
title = {Towards commoditized smart-camera design},
author = {Boštjan Murovec and Janez Perš and Rok Mandeljc and Vildana Sulić Kenk and Stanislav Kovačič},
url = {http://www.sciencedirect.com/science/article/pii/S1383762113000799},
doi = {https://doi.org/10.1016/j.sysarc.2013.05.010},
issn = {1383-7621},
year = {2013},
date = {2013-01-01},
journal = {Journal of Systems Architecture},
volume = {59},
number = {10, Part A},
pages = {847 - 858},
abstract = {We propose a set of design principles for a cost-effective embedded smart camera. Our aim is to alleviate the shortcomings of the existing designs, such as excessive reliance on battery power and wireless networking, over-emphasized focus on specific use cases, and use of specialized technologies. In our opinion, these shortcomings prevent widespread commercialization and adoption of embedded smart cameras, especially in the context of visual-sensor networks. The proposed principles lead to a distinctively different design, which relies on commoditized, standardized and widely-available components, tools and knowledge. As an example of using these principles in practice, we present a smart camera, which is inexpensive, easy to build and support, capable of high-speed communication and enables rapid transfer of computer-vision algorithms to the embedded world.},
note = {Smart Camera Architecture},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
We propose a set of design principles for a cost-effective embedded smart camera. Our aim is to alleviate the shortcomings of the existing designs, such as excessive reliance on battery power and wireless networking, over-emphasized focus on specific use cases, and use of specialized technologies. In our opinion, these shortcomings prevent widespread commercialization and adoption of embedded smart cameras, especially in the context of visual-sensor networks. The proposed principles lead to a distinctively different design, which relies on commoditized, standardized and widely-available components, tools and knowledge. As an example of using these principles in practice, we present a smart camera, which is inexpensive, easy to build and support, capable of high-speed communication and enables rapid transfer of computer-vision algorithms to the embedded world.
Proceedings Articles
Janez Križaj; Simon Dobrišek; Vitomir Štruc; Nikola Pavešić
Robust 3D face recognition using adapted statistical models Proceedings Article
V: Proceedings of the Electrotechnical and Computer Science Conference (ERK'13), 2013.
@inproceedings{krizajrobust,
title = {Robust 3D face recognition using adapted statistical models},
author = {Janez Križaj and Simon Dobrišek and Vitomir Štruc and Nikola Pavešić},
url = {https://lmi.fe.uni-lj.si/en/robust3dfacerecognitionusingadaptedstatisticalmodels/},
year = {2013},
date = {2013-09-20},
urldate = {2013-09-20},
booktitle = {Proceedings of the Electrotechnical and Computer Science Conference (ERK'13)},
abstract = {The paper presents a novel framework to 3D face recognition that exploits region covariance matrices (RCMs), Gaussian mixture models (GMMs) and support vector machine (SVM) classifiers. The proposed framework first combines several 3D face representations at the feature level using RCM descriptors and then derives low-dimensional feature vectors from the computed descriptors with the unscented transform. By doing so, it enables computations in Euclidean space, and makes Gaussian mixture modeling feasible. Finally, a support vector classifier is used for identity inference. As demonstrated by our experimental results on the FRGCv2 and UMB databases, the proposed framework is highly robust and exhibits desirable characteristics such as an inherent mechanism for data fusion (through the RCMs), the ability to examine local as well as global structures of the face with the same descriptor, the ability to integrate domain-specific prior knowledge into the modeling procedure and consequently to handle missing or unreliable data.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The paper presents a novel framework to 3D face recognition that exploits region covariance matrices (RCMs), Gaussian mixture models (GMMs) and support vector machine (SVM) classifiers. The proposed framework first combines several 3D face representations at the feature level using RCM descriptors and then derives low-dimensional feature vectors from the computed descriptors with the unscented transform. By doing so, it enables computations in Euclidean space, and makes Gaussian mixture modeling feasible. Finally, a support vector classifier is used for identity inference. As demonstrated by our experimental results on the FRGCv2 and UMB databases, the proposed framework is highly robust and exhibits desirable characteristics such as an inherent mechanism for data fusion (through the RCMs), the ability to examine local as well as global structures of the face with the same descriptor, the ability to integrate domain-specific prior knowledge into the modeling procedure and consequently to handle missing or unreliable data.
Vitomir Štruc; Jeneja Žganec Gros; Simon Dobrišek; Nikola Pavešić
Exploiting representation plurality for robust and efficient face recognition Proceedings Article
V: Proceedings of the 22nd Intenational Electrotechnical and Computer Science Conference (ERK'13), str. 121–124, Portorož, Slovenia, 2013.
@inproceedings{ERK2013_Struc,
title = {Exploiting representation plurality for robust and efficient face recognition},
author = {Vitomir Štruc and Jeneja Žganec Gros and Simon Dobrišek and Nikola Pavešić},
url = {https://lmi.fe.uni-lj.si/en/exploitingrepresentationpluralityforrobustandefficientfacerecognition/},
year = {2013},
date = {2013-09-01},
urldate = {2013-09-01},
booktitle = {Proceedings of the 22nd Intenational Electrotechnical and Computer Science Conference (ERK'13)},
volume = {vol. B},
pages = {121--124},
address = {Portorož, Slovenia},
abstract = {The paper introduces a novel approach to face recognition that exploits plurality of representation to achieve robust face recognition. The proposed approach was submitted as a representative of the University of Ljubljana and Alpineon d.o.o. to the 2013 face recognition competition that was held in conjunction with the IAPR International Conference on Biometrics and achieved the best overall recognition results among all competition participants. Here, we describe the basic characteristics of the submitted approach, elaborate on the results of the competition and, most importantly, present some general findings made during our development work that are of relevance to the broader (face recognition) research community.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The paper introduces a novel approach to face recognition that exploits plurality of representation to achieve robust face recognition. The proposed approach was submitted as a representative of the University of Ljubljana and Alpineon d.o.o. to the 2013 face recognition competition that was held in conjunction with the IAPR International Conference on Biometrics and achieved the best overall recognition results among all competition participants. Here, we describe the basic characteristics of the submitted approach, elaborate on the results of the competition and, most importantly, present some general findings made during our development work that are of relevance to the broader (face recognition) research community.
Janez Križaj; Vitomir Štruc; Simon Dobrišek
Combining 3D face representations using region covariance descriptors and statistical models Proceedings Article
V: Proceedings of the IEEE International Conference on Automatic Face and Gesture Recognition and Workshops (IEEE FG), Workshop on 3D Face Biometrics, IEEE, Shanghai, China, 2013.
@inproceedings{FG2013,
title = {Combining 3D face representations using region covariance descriptors and statistical models},
author = {Janez Križaj and Vitomir Štruc and Simon Dobrišek},
url = {https://lmi.fe.uni-lj.si/en/combining3dfacerepresentationsusingregioncovariancedescriptorsandstatisticalmodels/},
year = {2013},
date = {2013-05-01},
urldate = {2013-05-01},
booktitle = {Proceedings of the IEEE International Conference on Automatic Face and Gesture Recognition and Workshops (IEEE FG), Workshop on 3D Face Biometrics},
publisher = {IEEE},
address = {Shanghai, China},
abstract = {The paper introduces a novel framework for 3D face recognition that capitalizes on region covariance descriptors and Gaussian mixture models. The framework presents an elegant and coherent way of combining multiple facial representations, while simultaneously examining all computed representations at various levels of locality. The framework first computes a number of region covariance matrices/descriptors from different sized regions of several image representations and then adopts the unscented transform to derive low-dimensional feature vectors from the computed descriptors. By doing so, it enables computations in the Euclidean space, and makes Gaussian mixture modeling feasible. In the last step a support vector machine classification scheme is used to make a decision regarding the identity of the modeled input 3D face image. The proposed framework exhibits several desirable characteristics, such as an inherent mechanism for data fusion/integration (through the region covariance matrices), the ability to examine the facial images at different levels of locality, and the ability to integrate domain-specific prior knowledge into the modeling procedure. We assess the feasibility of the proposed framework on the Face Recognition Grand Challenge version 2 (FRGCv2) database with highly encouraging results.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The paper introduces a novel framework for 3D face recognition that capitalizes on region covariance descriptors and Gaussian mixture models. The framework presents an elegant and coherent way of combining multiple facial representations, while simultaneously examining all computed representations at various levels of locality. The framework first computes a number of region covariance matrices/descriptors from different sized regions of several image representations and then adopts the unscented transform to derive low-dimensional feature vectors from the computed descriptors. By doing so, it enables computations in the Euclidean space, and makes Gaussian mixture modeling feasible. In the last step a support vector machine classification scheme is used to make a decision regarding the identity of the modeled input 3D face image. The proposed framework exhibits several desirable characteristics, such as an inherent mechanism for data fusion/integration (through the region covariance matrices), the ability to examine the facial images at different levels of locality, and the ability to integrate domain-specific prior knowledge into the modeling procedure. We assess the feasibility of the proposed framework on the Face Recognition Grand Challenge version 2 (FRGCv2) database with highly encouraging results.
Vitomir Štruc; Nikola Pavešić; Jerneja Žganec-Gros; Boštjan Vesnicer
Patch-wise low-dimensional probabilistic linear discriminant analysis for Face Recognition Proceedings Article
V: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), str. 2352–2356, IEEE 2013.
@inproceedings{vstruc2013patch,
title = {Patch-wise low-dimensional probabilistic linear discriminant analysis for Face Recognition},
author = {Vitomir Štruc and Nikola Pavešić and Jerneja Žganec-Gros and Boštjan Vesnicer},
url = {https://lmi.fe.uni-lj.si/en/patch-wiselow-dimensionalprobabilisticlineardiscriminantanalysisforfacerecognition/},
doi = {10.1109/ICASSP.2013.6638075},
year = {2013},
date = {2013-01-01},
urldate = {2013-01-01},
booktitle = {2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
pages = {2352--2356},
organization = {IEEE},
abstract = {The paper introduces a novel approach to face recognition based on the recently proposed low-dimensional probabilistic linear discriminant analysis (LD-PLDA). The proposed approach is specifically designed for complex recognition tasks, where highly nonlinear face variations are typically encountered. Such data variations are commonly induced by changes in the external illumination conditions, viewpoint changes or expression variations and represent quite a challenge even for state-of-the-art techniques, such as LD-PLDA. To overcome this problem, we propose here a patch-wise form of the LDPLDA technique (i.e., PLD-PLDA), which relies on local image patches rather than the entire image to make inferences about the identity of the input images. The basic idea here is to decompose the complex face recognition problem into simpler problems, for which the linear nature of the LD-PLDA technique may be better suited. By doing so, several similarity scores are derived from one facial image, which are combined at the final stage using a simple sum-rule fusion scheme to arrive at a single score that can be employed for identity inference. We evaluate the proposed technique on experiment 4 of the Face Recognition Grand Challenge (FRGCv2) database with highly promising results.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The paper introduces a novel approach to face recognition based on the recently proposed low-dimensional probabilistic linear discriminant analysis (LD-PLDA). The proposed approach is specifically designed for complex recognition tasks, where highly nonlinear face variations are typically encountered. Such data variations are commonly induced by changes in the external illumination conditions, viewpoint changes or expression variations and represent quite a challenge even for state-of-the-art techniques, such as LD-PLDA. To overcome this problem, we propose here a patch-wise form of the LDPLDA technique (i.e., PLD-PLDA), which relies on local image patches rather than the entire image to make inferences about the identity of the input images. The basic idea here is to decompose the complex face recognition problem into simpler problems, for which the linear nature of the LD-PLDA technique may be better suited. By doing so, several similarity scores are derived from one facial image, which are combined at the final stage using a simple sum-rule fusion scheme to arrive at a single score that can be employed for identity inference. We evaluate the proposed technique on experiment 4 of the Face Recognition Grand Challenge (FRGCv2) database with highly promising results.
Manuel Günther; Artur Costa-Pazo; Changxing Ding; Elhocine Boutellaa; Giovani Chiachia; Honglei Zhang; Marcus Assis de Angeloni; Vitomir Štruc; Elie Khoury; Esteban Vazquez-Fernandez; others
The 2013 face recognition evaluation in mobile environment Proceedings Article
V: Proceedings of the IAPR International Conference on Biometrics (ICB), str. 1–7, IAPR 2013.
@inproceedings{gunther20132013,
title = {The 2013 face recognition evaluation in mobile environment},
author = {Manuel Günther and Artur Costa-Pazo and Changxing Ding and Elhocine Boutellaa and Giovani Chiachia and Honglei Zhang and Marcus Assis de Angeloni and Vitomir Štruc and Elie Khoury and Esteban Vazquez-Fernandez and others},
url = {https://lmi.fe.uni-lj.si/en/the2013facerecognitionevaluationinmobileenvironment/},
year = {2013},
date = {2013-01-01},
urldate = {2013-01-01},
booktitle = {Proceedings of the IAPR International Conference on Biometrics (ICB)},
pages = {1--7},
organization = {IAPR},
abstract = {Automatic face recognition in unconstrained environments is a challenging task. To test current trends in face recognition algorithms, we organized an evaluation on face recognition in mobile environment. This paper presents the results of 8 different participants using two verification metrics. Most submitted algorithms rely on one or more of three types of features: local binary patterns, Gabor wavelet responses including Gabor phases, and color information. The best results are obtained from UNILJ-ALP, which fused several image representations and feature types, and UCHU, which learns optimal features with a convolutional neural network. Additionally, we assess the usability of the algorithms in mobile devices with limited resources.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Automatic face recognition in unconstrained environments is a challenging task. To test current trends in face recognition algorithms, we organized an evaluation on face recognition in mobile environment. This paper presents the results of 8 different participants using two verification metrics. Most submitted algorithms rely on one or more of three types of features: local binary patterns, Gabor wavelet responses including Gabor phases, and color information. The best results are obtained from UNILJ-ALP, which fused several image representations and feature types, and UCHU, which learns optimal features with a convolutional neural network. Additionally, we assess the usability of the algorithms in mobile devices with limited resources.
2012
Journal Articles
Janez Križaj; Vitomir Štruc; Simon Dobrišek
Robust 3D Face Recognition Članek v strokovni reviji
V: Electrotechnical Review, vol. 79, no. 1-2, str. 1-6, 2012.
@article{Križaj-EV-2012,
title = {Robust 3D Face Recognition},
author = {Janez Križaj and Vitomir Štruc and Simon Dobrišek},
url = {https://lmi.fe.uni-lj.si/en/robust3dfacerecognition/},
year = {2012},
date = {2012-06-01},
urldate = {2012-06-01},
journal = {Electrotechnical Review},
volume = {79},
number = {1-2},
pages = {1-6},
abstract = {Face recognition in uncontrolled environments is hindered by variations in illumination, pose, expression and occlusions of faces. Many practical face-recognition systems are affected by these variations. One way to increase the robustness to illumination and pose variations is to use 3D facial images. In this paper 3D face-recognition systems are presented. Their structure and operation are described. The robustness of such systems to variations in uncontrolled environments is emphasized. We present some preliminary results of a system developed in our laboratory.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Face recognition in uncontrolled environments is hindered by variations in illumination, pose, expression and occlusions of faces. Many practical face-recognition systems are affected by these variations. One way to increase the robustness to illumination and pose variations is to use 3D facial images. In this paper 3D face-recognition systems are presented. Their structure and operation are described. The robustness of such systems to variations in uncontrolled environments is emphasized. We present some preliminary results of a system developed in our laboratory.
Janez Križaj; Vitomir Štruc; Simon Dobrišek
Towards robust 3D face verification using Gaussian mixture models Članek v strokovni reviji
V: International Journal of Advanced Robotic Systems, vol. 9, 2012.
@article{krizaj2012towards,
title = {Towards robust 3D face verification using Gaussian mixture models},
author = {Janez Križaj and Vitomir Štruc and Simon Dobrišek},
url = {https://lmi.fe.uni-lj.si/en/towardsrobust3dfaceverificationusinggaussianmixturemodels/},
doi = {10.5772/52200},
year = {2012},
date = {2012-01-01},
urldate = {2012-01-01},
journal = {International Journal of Advanced Robotic Systems},
volume = {9},
publisher = {InTech},
abstract = {This paper focuses on the use of Gaussian Mixture models (GMM) for 3D face verification. A special interest is taken in practical aspects of 3D face verification systems, where all steps of the verification procedure need to be automated and no meta-data, such as pre-annotated eye/nose/mouth positions, is available to the system. In such settings the performance of the verification system correlates heavily with the performance of the employed alignment (i.e., geometric normalization) procedure. We show that popular holistic as well as local recognition techniques, such as principal component analysis (PCA), or Scale-invariant feature transform (SIFT)-based methods considerably deteriorate in their performance when an “imperfect” geometric normalization procedure is used to align the 3D face scans and that in these situations GMMs should be preferred. Moreover, several possibilities to improve the performance and robustness of the classical GMM framework are presented and evaluated: i) explicit inclusion of spatial information, during the GMM construction procedure, ii) implicit inclusion of spatial information during the GMM construction procedure and iii) on-line evaluation and possible rejection of local feature vectors based on their likelihood. We successfully demonstrate the feasibility of the proposed modifications on the Face Recognition Grand Challenge data set.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This paper focuses on the use of Gaussian Mixture models (GMM) for 3D face verification. A special interest is taken in practical aspects of 3D face verification systems, where all steps of the verification procedure need to be automated and no meta-data, such as pre-annotated eye/nose/mouth positions, is available to the system. In such settings the performance of the verification system correlates heavily with the performance of the employed alignment (i.e., geometric normalization) procedure. We show that popular holistic as well as local recognition techniques, such as principal component analysis (PCA), or Scale-invariant feature transform (SIFT)-based methods considerably deteriorate in their performance when an “imperfect” geometric normalization procedure is used to align the 3D face scans and that in these situations GMMs should be preferred. Moreover, several possibilities to improve the performance and robustness of the classical GMM framework are presented and evaluated: i) explicit inclusion of spatial information, during the GMM construction procedure, ii) implicit inclusion of spatial information during the GMM construction procedure and iii) on-line evaluation and possible rejection of local feature vectors based on their likelihood. We successfully demonstrate the feasibility of the proposed modifications on the Face Recognition Grand Challenge data set.
Bostjan Vesnicer; Jerneja Žganec Gros; Nikola Pavešić; Vitomir Štruc
Face recognition using simplified probabilistic linear discriminant analysis Članek v strokovni reviji
V: International Journal of Advanced Robotic Systems, vol. 9, 2012.
@article{vesnicer2012face,
title = {Face recognition using simplified probabilistic linear discriminant analysis},
author = {Bostjan Vesnicer and Jerneja Žganec Gros and Nikola Pavešić and Vitomir Štruc},
url = {https://lmi.fe.uni-lj.si/en/facerecognitionusingsimplifiedprobabilisticlineardiscriminantanalysis/},
doi = {10.5772/52258},
year = {2012},
date = {2012-01-01},
urldate = {2012-01-01},
journal = {International Journal of Advanced Robotic Systems},
volume = {9},
publisher = {InTech},
abstract = {Face recognition in uncontrolled environments remains an open problem that has not been satisfactorily solved by existing recognition techniques. In this paper, we tackle this problem using a variant of the recently proposed Probabilistic Linear Discriminant Analysis (PLDA). We show that simplified versions of the PLDA model, which are regularly used in the field of speaker recognition, rely on certain assumptions that not only result in a simpler PLDA model, but also reduce the computational load of the technique and - as indicated by our experimental assessments - improve recognition performance. Moreover, we show that, contrary to the general belief that PLDA-based methods produce well calibrated verification scores, score normalization techniques can still deliver significant performance gains, but only if non-parametric score normalization techniques are employed. Last but not least, we demonstrate the competitiveness of the simplified PLDA model for face recognition by comparing our results with the state-of-the-art results from the literature obtained on the second version of the large-scale Face Recognition Grand Challenge (FRGC) database.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Face recognition in uncontrolled environments remains an open problem that has not been satisfactorily solved by existing recognition techniques. In this paper, we tackle this problem using a variant of the recently proposed Probabilistic Linear Discriminant Analysis (PLDA). We show that simplified versions of the PLDA model, which are regularly used in the field of speaker recognition, rely on certain assumptions that not only result in a simpler PLDA model, but also reduce the computational load of the technique and - as indicated by our experimental assessments - improve recognition performance. Moreover, we show that, contrary to the general belief that PLDA-based methods produce well calibrated verification scores, score normalization techniques can still deliver significant performance gains, but only if non-parametric score normalization techniques are employed. Last but not least, we demonstrate the competitiveness of the simplified PLDA model for face recognition by comparing our results with the state-of-the-art results from the literature obtained on the second version of the large-scale Face Recognition Grand Challenge (FRGC) database.
2011
Book Sections
Vitomir Štruc; Nikola Pavešić
Photometric normalization techniques for illumination invariance Book Section
V: Zhang, Yu-Jin (Ur.): Advances in Face Image Analysis: Techniques and Technologies, str. 279-300, IGI-Global, 2011.
@incollection{IGI2011,
title = {Photometric normalization techniques for illumination invariance},
author = {Vitomir Štruc and Nikola Pavešić},
editor = {Yu-Jin Zhang},
url = {https://lmi.fe.uni-lj.si/en/photometricnormalizationtechniquesforilluminationinvariance/},
doi = {10.4018/978-1-61520-991-0.ch015},
year = {2011},
date = {2011-01-01},
urldate = {2011-01-01},
booktitle = {Advances in Face Image Analysis: Techniques and Technologies},
pages = {279-300},
publisher = {IGI-Global},
abstract = {Face recognition technology has come a long way since its beginnings in the previous century. Due to its countless application possibilities, it has attracted the interest of research groups from universities and companies around the world. Thanks to this enormous research effort, the recognition rates achievable with the state-of-the-art face recognition technology are steadily growing, even though some issues still pose major challenges to the technology. Amongst these challenges, coping with illumination-induced appearance variations is one of the biggest and still not satisfactorily solved. A number of techniques have been proposed in the literature to cope with the impact of illumination ranging from simple image enhancement techniques, such as histogram equalization, to more elaborate methods, such as anisotropic smoothing or the logarithmic total variation model. This chapter presents an overview of the most popular and efficient normalization techniques that try to solve the illumination variation problem at the preprocessing level. It assesses the techniques on the YaleB and XM2VTS databases and explores their strengths and weaknesses from the theoretical and implementation point of view.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Face recognition technology has come a long way since its beginnings in the previous century. Due to its countless application possibilities, it has attracted the interest of research groups from universities and companies around the world. Thanks to this enormous research effort, the recognition rates achievable with the state-of-the-art face recognition technology are steadily growing, even though some issues still pose major challenges to the technology. Amongst these challenges, coping with illumination-induced appearance variations is one of the biggest and still not satisfactorily solved. A number of techniques have been proposed in the literature to cope with the impact of illumination ranging from simple image enhancement techniques, such as histogram equalization, to more elaborate methods, such as anisotropic smoothing or the logarithmic total variation model. This chapter presents an overview of the most popular and efficient normalization techniques that try to solve the illumination variation problem at the preprocessing level. It assesses the techniques on the YaleB and XM2VTS databases and explores their strengths and weaknesses from the theoretical and implementation point of view.
Proceedings Articles
Vitomir Štruc; Jerneja Žganec-Gros; Nikola Pavešić
Principal directions of synthetic exact filters for robust real-time eye localization Proceedings Article
V: Proceedings of the COST workshop on Biometrics and Identity Management (BioID), str. 180/192, Springer-Verlag, Berlin, Heidelberg, 2011.
@inproceedings{BioID_Struc_2011,
title = {Principal directions of synthetic exact filters for robust real-time eye localization},
author = {Vitomir Štruc and Jerneja Žganec-Gros and Nikola Pavešić},
url = {https://lmi.fe.uni-lj.si/en/principaldirectionsofsyntheticexactfiltersforrobustreal-timeeyelocalization/},
doi = {10.1007/978-3-642-19530-3_17},
year = {2011},
date = {2011-01-01},
urldate = {2011-01-01},
booktitle = {Proceedings of the COST workshop on Biometrics and Identity Management (BioID)},
volume = {6583/2011},
pages = {180/192},
publisher = {Springer-Verlag},
address = {Berlin, Heidelberg},
series = {Lecture Notes on Computer Science},
abstract = {The alignment of the facial region with a predefined canonical form is one of the most crucial steps in a face recognition system. Most of the existing alignment techniques rely on the position of the eyes and, hence, require an efficient and reliable eye localization procedure. In this paper we propose a novel technique for this purpose, which exploits a new class of correlation filters called Principal directions of Synthetic Exact Filters (PSEFs). The proposed filters represent a generalization of the recently proposed Average of Synthetic Exact Filters (ASEFs) and exhibit desirable properties, such as relatively short training times, computational simplicity, high localization rates and real time capabilities. We present the theory of PSEF filter construction, elaborate on their characteristics and finally develop an efficient procedure for eye localization using several PSEF filters. We demonstrate the effectiveness of the proposed class of correlation filters for the task of eye localization on facial images from the FERET database and show that for the tested task they outperform the established Haar cascade object detector as well as the ASEF correlation filters.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The alignment of the facial region with a predefined canonical form is one of the most crucial steps in a face recognition system. Most of the existing alignment techniques rely on the position of the eyes and, hence, require an efficient and reliable eye localization procedure. In this paper we propose a novel technique for this purpose, which exploits a new class of correlation filters called Principal directions of Synthetic Exact Filters (PSEFs). The proposed filters represent a generalization of the recently proposed Average of Synthetic Exact Filters (ASEFs) and exhibit desirable properties, such as relatively short training times, computational simplicity, high localization rates and real time capabilities. We present the theory of PSEF filter construction, elaborate on their characteristics and finally develop an efficient procedure for eye localization using several PSEF filters. We demonstrate the effectiveness of the proposed class of correlation filters for the task of eye localization on facial images from the FERET database and show that for the tested task they outperform the established Haar cascade object detector as well as the ASEF correlation filters.
2010
Journal Articles
Vitomir Štruc; Nikola Pavešić
The Complete Gabor-Fisher Classifier for Robust Face Recognition Članek v strokovni reviji
V: EURASIP Advances in Signal Processing, vol. 2010, str. 26, 2010.
@article{CGF-Struc_2010,
title = {The Complete Gabor-Fisher Classifier for Robust Face Recognition},
author = {Vitomir Štruc and Nikola Pavešić},
url = {https://lmi.fe.uni-lj.si/en/thecompletegabor-fisherclassifierforrobustfacerecognition/},
doi = {10.1155/2010/847680},
year = {2010},
date = {2010-01-01},
urldate = {2010-01-01},
journal = {EURASIP Advances in Signal Processing},
volume = {2010},
pages = {26},
abstract = {This paper develops a novel face recognition technique called Complete Gabor Fisher Classifier (CGFC). Different from existing techniques that use Gabor filters for deriving the Gabor face representation, the proposed approach does not rely solely on Gabor magnitude information but effectively uses features computed based on Gabor phase information as well. It represents one of the few successful attempts found in the literature of combining Gabor magnitude and phase information for robust face recognition. The novelty of the proposed CGFC technique comes from (1) the introduction of a Gabor phase-based face representation and (2) the combination of the recognition technique using the proposed representation with classical Gabor magnitude-based methods into a unified framework. The proposed face recognition framework is assessed in a series of face verification and identification experiments performed on the XM2VTS, Extended YaleB, FERET, and AR databases. The results of the assessment suggest that the proposed technique clearly outperforms state-of-the-art face recognition techniques from the literature and that its performance is almost unaffected by the presence of partial occlusions of the facial area, changes in facial expression, or severe illumination changes.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This paper develops a novel face recognition technique called Complete Gabor Fisher Classifier (CGFC). Different from existing techniques that use Gabor filters for deriving the Gabor face representation, the proposed approach does not rely solely on Gabor magnitude information but effectively uses features computed based on Gabor phase information as well. It represents one of the few successful attempts found in the literature of combining Gabor magnitude and phase information for robust face recognition. The novelty of the proposed CGFC technique comes from (1) the introduction of a Gabor phase-based face representation and (2) the combination of the recognition technique using the proposed representation with classical Gabor magnitude-based methods into a unified framework. The proposed face recognition framework is assessed in a series of face verification and identification experiments performed on the XM2VTS, Extended YaleB, FERET, and AR databases. The results of the assessment suggest that the proposed technique clearly outperforms state-of-the-art face recognition techniques from the literature and that its performance is almost unaffected by the presence of partial occlusions of the facial area, changes in facial expression, or severe illumination changes.
Norman Poh; Chi Ho Chan; Josef Kittler; Sebastien Marcel; Christopher Mc Cool; Enrique Argones Rua; Jose Luis Alba Castro; Mauricio Villegas; Roberto Paredes; Vitomir Struc; others
An evaluation of video-to-video face verification Članek v strokovni reviji
V: IEEE Transactions on Information Forensics and Security, vol. 5, no. 4, str. 781–801, 2010.
@article{poh2010evaluation,
title = {An evaluation of video-to-video face verification},
author = {Norman Poh and Chi Ho Chan and Josef Kittler and Sebastien Marcel and Christopher Mc Cool and Enrique Argones Rua and Jose Luis Alba Castro and Mauricio Villegas and Roberto Paredes and Vitomir Struc and others},
url = {https://lmi.fe.uni-lj.si/en/anevaluationofvideo-to-videofaceverification/},
doi = {10.1109/TIFS.2010.2077627},
year = {2010},
date = {2010-01-01},
urldate = {2010-01-01},
journal = {IEEE Transactions on Information Forensics and Security},
volume = {5},
number = {4},
pages = {781--801},
publisher = {IEEE},
abstract = {Person recognition using facial features, e.g., mug-shot images, has long been used in identity documents. However, due to the widespread use of web-cams and mobile devices embedded with a camera, it is now possible to realize facial video recognition, rather than resorting to just still images. In fact, facial video recognition offers many advantages over still image recognition; these include the potential of boosting the system accuracy and deterring spoof attacks. This paper presents an evaluation of person identity verification using facial video data, organized in conjunction with the International Conference on Biometrics (ICB 2009). It involves 18 systems submitted by seven academic institutes. These systems provide for a diverse set of assumptions, including feature representation and preprocessing variations, allowing us to assess the effect of adverse conditions, usage of quality information, query selection, and template construction for video-to-video face authentication.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Person recognition using facial features, e.g., mug-shot images, has long been used in identity documents. However, due to the widespread use of web-cams and mobile devices embedded with a camera, it is now possible to realize facial video recognition, rather than resorting to just still images. In fact, facial video recognition offers many advantages over still image recognition; these include the potential of boosting the system accuracy and deterring spoof attacks. This paper presents an evaluation of person identity verification using facial video data, organized in conjunction with the International Conference on Biometrics (ICB 2009). It involves 18 systems submitted by seven academic institutes. These systems provide for a diverse set of assumptions, including feature representation and preprocessing variations, allowing us to assess the effect of adverse conditions, usage of quality information, query selection, and template construction for video-to-video face authentication.
Boštjan Murovec; James M Tiedje; Blaž Stres
DNA encoding for an efficient 'Omics processing Članek v strokovni reviji
V: Computer Methods and Programs in Biomedicine, vol. 100, no. 2, str. 175 - 190, 2010, ISSN: 0169-2607.
@article{MUROVEC2010175,
title = {DNA encoding for an efficient 'Omics processing},
author = {Boštjan Murovec and James M Tiedje and Blaž Stres},
url = {http://www.sciencedirect.com/science/article/pii/S0169260710000660},
doi = {https://doi.org/10.1016/j.cmpb.2010.03.014},
issn = {0169-2607},
year = {2010},
date = {2010-01-01},
journal = {Computer Methods and Programs in Biomedicine},
volume = {100},
number = {2},
pages = {175 - 190},
abstract = {The exponential growth of available DNA sequences and the increased interoperability of biological information is triggering intergovernmental efforts aimed at increasing the access, dissemination, and analysis of sequence data. Achieving the efficient storage and processing of DNA material is an important goal that parallels well with the foreseen coding standardization on the horizon. This paper proposes novel coding approaches, for both the dissemination and processing of sequences, where the speed of the DNA processing is shown to be boosted by exploring more than the normally utilized eight bits for encoding a single nucleotide. Further gains are achieved by encoding the nucleotides together with their trailing alignment information as a single 64-bit data structure. The paper also proposes a slight modification to the established FASTA scheme in order to improve on its representation of alignment information. The significance of the propositions is confirmed by the encouraging results from empirical tests.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The exponential growth of available DNA sequences and the increased interoperability of biological information is triggering intergovernmental efforts aimed at increasing the access, dissemination, and analysis of sequence data. Achieving the efficient storage and processing of DNA material is an important goal that parallels well with the foreseen coding standardization on the horizon. This paper proposes novel coding approaches, for both the dissemination and processing of sequences, where the speed of the DNA processing is shown to be boosted by exploring more than the normally utilized eight bits for encoding a single nucleotide. Further gains are achieved by encoding the nucleotides together with their trailing alignment information as a single 64-bit data structure. The paper also proposes a slight modification to the established FASTA scheme in order to improve on its representation of alignment information. The significance of the propositions is confirmed by the encouraging results from empirical tests.
Book Sections
Vitomir Štruc; Nikola Pavešić
V: Oravec, Milos (Ur.): Face Recognition, str. 215-238, In-Tech, Vienna, 2010.
@incollection{InTech2010,
title = {From Gabor Magnitude to Gabor Phase Features: Tackling the Problem of Face Recognition under Severe Illumination Changes},
author = {Vitomir Štruc and Nikola Pavešić},
editor = {Milos Oravec},
url = {https://lmi.fe.uni-lj.si/en/fromgabormagnitudetogaborphasefeaturestacklingtheproblemoffacerecognitionundersevereilluminationchanges/},
doi = {10.5772/8938},
year = {2010},
date = {2010-01-01},
urldate = {2010-01-01},
booktitle = {Face Recognition},
pages = {215-238},
publisher = {In-Tech},
address = {Vienna},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Proceedings Articles
Vitomir Štruc; Nikola Pavešić
Face recogniton from color images using sparse projection analysis Proceedings Article
V: Proceedings of the 7th International Conference on Image Analysis and Recognition (ICIAR 2010), str. 445-453, Povoa de Varzim, Portugal, 2010.
@inproceedings{ICIAR2010_Sparse,
title = {Face recogniton from color images using sparse projection analysis},
author = {Vitomir Štruc and Nikola Pavešić},
url = {https://lmi.fe.uni-lj.si/en/facerecognitonfromcolorimagesusingsparseprojectionanalysis/},
year = {2010},
date = {2010-06-01},
urldate = {2010-06-01},
booktitle = {Proceedings of the 7th International Conference on Image Analysis and Recognition (ICIAR 2010)},
pages = {445-453},
address = {Povoa de Varzim, Portugal},
abstract = {The paper presents a novel feature extraction technique for face recognition which uses sparse projection axes to compute a lowdimensional representation of face images. The proposed technique derives the sparse axes by first recasting the problem of face recognition as a regression problem and then solving the new (under-determined) regression problem by computing the solution with minimum L1 norm. The developed technique, named Sparse Projection Analysis (SPA), is applied to color as well as grey-scale images from the XM2VTS database and compared to popular subspace projection techniques (with sparse and dense projection axes) from the literature. The results of the experimental assessment show that the proposed technique ensures promising results on un-occluded as well occluded images from the XM2VTS database.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The paper presents a novel feature extraction technique for face recognition which uses sparse projection axes to compute a lowdimensional representation of face images. The proposed technique derives the sparse axes by first recasting the problem of face recognition as a regression problem and then solving the new (under-determined) regression problem by computing the solution with minimum L1 norm. The developed technique, named Sparse Projection Analysis (SPA), is applied to color as well as grey-scale images from the XM2VTS database and compared to popular subspace projection techniques (with sparse and dense projection axes) from the literature. The results of the experimental assessment show that the proposed technique ensures promising results on un-occluded as well occluded images from the XM2VTS database.
Janez Križaj; Vitomir Štruc; Nikola Pavešić
Adaptation of SIFT Features for Robust Face Recognition Proceedings Article
V: Proceedings of the 7th International Conference on Image Analysis and Recognition (ICIAR 2010), str. 394-404, Povoa de Varzim, Portugal, 2010.
@inproceedings{ICIAR2010_Sift,
title = {Adaptation of SIFT Features for Robust Face Recognition},
author = {Janez Križaj and Vitomir Štruc and Nikola Pavešić},
url = {https://lmi.fe.uni-lj.si/en/adaptationofsiftfeaturesforrobustfacerecognition/},
year = {2010},
date = {2010-06-01},
urldate = {2010-06-01},
booktitle = {Proceedings of the 7th International Conference on Image Analysis and Recognition (ICIAR 2010)},
pages = {394-404},
address = {Povoa de Varzim, Portugal},
abstract = {The Scale Invariant Feature Transform (SIFT) is an algorithm used to detect and describe scale-, translation- and rotation-invariant local features in images. The original SIFT algorithm has been successfully applied in general object detection and recognition tasks, panorama stitching and others. One of its more recent uses also includes face recognition, where it was shown to deliver encouraging results. SIFT-based face recognition techniques found in the literature rely heavily on the so-called keypoint detector, which locates interest points in the given image that are ultimately used to compute the SIFT descriptors. While these descriptors are known to be among others (partially) invariant to illumination changes, the keypoint detector is not. Since varying illumination is one of the main issues affecting the performance of face recognition systems, the keypoint detector represents the main source of errors in face recognition systems relying on SIFT features. To overcome the presented shortcoming of SIFT-based methods, we present in this paper a novel face recognition technique that computes the SIFT descriptors at predefined (fixed) locations learned during the training stage. By doing so, it eliminates the need for keypoint detection on the test images and renders our approach more robust to illumination changes than related approaches from the literature. Experiments, performed on the Extended Yale B face database, show that the proposed technique compares favorably with several popular techniques from the literature in terms of performance.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The Scale Invariant Feature Transform (SIFT) is an algorithm used to detect and describe scale-, translation- and rotation-invariant local features in images. The original SIFT algorithm has been successfully applied in general object detection and recognition tasks, panorama stitching and others. One of its more recent uses also includes face recognition, where it was shown to deliver encouraging results. SIFT-based face recognition techniques found in the literature rely heavily on the so-called keypoint detector, which locates interest points in the given image that are ultimately used to compute the SIFT descriptors. While these descriptors are known to be among others (partially) invariant to illumination changes, the keypoint detector is not. Since varying illumination is one of the main issues affecting the performance of face recognition systems, the keypoint detector represents the main source of errors in face recognition systems relying on SIFT features. To overcome the presented shortcoming of SIFT-based methods, we present in this paper a novel face recognition technique that computes the SIFT descriptors at predefined (fixed) locations learned during the training stage. By doing so, it eliminates the need for keypoint detection on the test images and renders our approach more robust to illumination changes than related approaches from the literature. Experiments, performed on the Extended Yale B face database, show that the proposed technique compares favorably with several popular techniques from the literature in terms of performance.
Vitomir Štruc; Boštjan Vesnicer; France Mihelič; Nikola Pavešić
Removing Illumination Artifacts from Face Images using the Nuisance Attribute Projection Proceedings Article
V: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'10), str. 846-849, IEEE, Dallas, Texas, USA, 2010.
@inproceedings{ICASSP2010,
title = {Removing Illumination Artifacts from Face Images using the Nuisance Attribute Projection},
author = {Vitomir Štruc and Boštjan Vesnicer and France Mihelič and Nikola Pavešić},
url = {https://lmi.fe.uni-lj.si/en/removingilluminationartifactsfromfaceimagesusingthenuisanceattributeprojection/},
doi = {10.1109/ICASSP.2010.5495203},
year = {2010},
date = {2010-03-01},
urldate = {2010-03-01},
booktitle = {Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'10)},
pages = {846-849},
publisher = {IEEE},
address = {Dallas, Texas, USA},
abstract = {Illumination induced appearance changes represent one of the open challenges in automated face recognition systems still significantly influencing their performance. Several techniques have been presented in the literature to cope with this problem; however, a universal solution remains to be found. In this paper we present a novel normalization scheme based on the nuisance attribute projection (NAP), which tries to remove the effects of illumination by projecting away multiple dimensions of a low dimensional illumination subspace. The technique is assessed in face recognition experiments performed on the extended YaleB and XM2VTS databases. Comparative results with state-of-the-art techniques show the competitiveness of the proposed technique.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Illumination induced appearance changes represent one of the open challenges in automated face recognition systems still significantly influencing their performance. Several techniques have been presented in the literature to cope with this problem; however, a universal solution remains to be found. In this paper we present a novel normalization scheme based on the nuisance attribute projection (NAP), which tries to remove the effects of illumination by projecting away multiple dimensions of a low dimensional illumination subspace. The technique is assessed in face recognition experiments performed on the extended YaleB and XM2VTS databases. Comparative results with state-of-the-art techniques show the competitiveness of the proposed technique.
Vitomir Štruc; Simon Dobrišek; Nikola Pavešić
Confidence Weighted Subspace Projection Techniques for Robust Face Recognition in the Presence of Partial Occlusions Proceedings Article
V: Proceedings of the International Conference on Pattern Recognition (ICPR'10), str. 1334-1338, Istanbul, Turkey, 2010.
@inproceedings{ICPR_Struc_2010,
title = {Confidence Weighted Subspace Projection Techniques for Robust Face Recognition in the Presence of Partial Occlusions},
author = {Vitomir Štruc and Simon Dobrišek and Nikola Pavešić},
url = {https://lmi.fe.uni-lj.si/en/confidenceweightedsubspaceprojectiontechniquesforrobustfacerecognitioninthepresenceofpartialocclusions/},
year = {2010},
date = {2010-01-01},
urldate = {2010-01-01},
booktitle = {Proceedings of the International Conference on Pattern Recognition (ICPR'10)},
pages = {1334-1338},
address = {Istanbul, Turkey},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Rok Gajšek; Vitomir Štruc; France Mihelič
Multi-modal Emotion Recognition using Canonical Correlations and Acustic Features Proceedings Article
V: Proceedings of the International Conference on Pattern Recognition (ICPR), str. 4133-4136, IAPR Istanbul, Turkey, 2010.
@inproceedings{ICPR_Gajsek_2010,
title = {Multi-modal Emotion Recognition using Canonical Correlations and Acustic Features},
author = {Rok Gajšek and Vitomir Štruc and France Mihelič},
url = {https://lmi.fe.uni-lj.si/en/multi-modalemotionrecognitionusingcanonicalcorrelationsandacusticfeatures/},
year = {2010},
date = {2010-01-01},
urldate = {2010-01-01},
booktitle = {Proceedings of the International Conference on Pattern Recognition (ICPR)},
pages = {4133-4136},
address = {Istanbul, Turkey},
organization = {IAPR},
abstract = {The information of the psycho-physical state of the subject is becoming a valuable addition to the modern audio or video recognition systems. As well as enabling a better user experience, it can also assist in superior recognition accuracy of the base system. In the article, we present our approach to multi-modal (audio-video) emotion recognition system. For audio sub-system, a feature set comprised of prosodic, spectral and cepstrum features is selected and support vector classifier is used to produce the scores for each emotional category. For video sub-system a novel approach is presented, which does not rely on the tracking of specific facial landmarks and thus, eliminates the problems usually caused, if the tracking algorithm fails at detecting the correct area. The system is evaluated on the eNTERFACE database and the recognition accuracy of our audio-video fusion is compared to the published results in the literature.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The information of the psycho-physical state of the subject is becoming a valuable addition to the modern audio or video recognition systems. As well as enabling a better user experience, it can also assist in superior recognition accuracy of the base system. In the article, we present our approach to multi-modal (audio-video) emotion recognition system. For audio sub-system, a feature set comprised of prosodic, spectral and cepstrum features is selected and support vector classifier is used to produce the scores for each emotional category. For video sub-system a novel approach is presented, which does not rely on the tracking of specific facial landmarks and thus, eliminates the problems usually caused, if the tracking algorithm fails at detecting the correct area. The system is evaluated on the eNTERFACE database and the recognition accuracy of our audio-video fusion is compared to the published results in the literature.
Rok Gajšek; Vitomir Štruc; France Mihelič
Multi-modal Emotion Recognition based on the Decoupling of Emotion and Speaker Information Proceedings Article
V: Proceedings of Text, Speech and Dialogue (TSD), str. 275-282, Springer-Verlag, Berlin, Heidelberg, 2010.
@inproceedings{TSD_Emo_Gajsek,
title = {Multi-modal Emotion Recognition based on the Decoupling of Emotion and Speaker Information},
author = {Rok Gajšek and Vitomir Štruc and France Mihelič},
url = {https://lmi.fe.uni-lj.si/en/multi-modalemotionrecognitionbasedonthedecouplingofemotionandspeakerinformation/},
year = {2010},
date = {2010-01-01},
urldate = {2010-01-01},
booktitle = {Proceedings of Text, Speech and Dialogue (TSD)},
volume = {6231/2010},
pages = {275-282},
publisher = {Springer-Verlag},
address = {Berlin, Heidelberg},
series = {Lecture Notes on Computer Science},
abstract = {The standard features used in emotion recognition carry, besides the emotion related information, also cues about the speaker. This is expected, since the nature of emotionally colored speech is similar to the variations in the speech signal, caused by different speakers. Therefore, we present a gradient descent derived transformation for the decoupling of emotion and speaker information contained in the acoustic features. The Interspeech ’09 Emotion Challenge feature set is used as the baseline for the audio part. A similar procedure is employed on the video signal, where the nuisance attribute projection (NAP) is used to derive the transformation matrix, which contains information about the emotional state of the speaker. Ultimately, different NAP transformation matrices are compared using canonical correlations. The audio and video sub-systems are combined at the matching score level using different fusion techniques. The presented system is assessed on the publicly available eNTERFACE’05 database where significant improvements in the recognition performance are observed when compared to the stat-of-the-art baseline.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The standard features used in emotion recognition carry, besides the emotion related information, also cues about the speaker. This is expected, since the nature of emotionally colored speech is similar to the variations in the speech signal, caused by different speakers. Therefore, we present a gradient descent derived transformation for the decoupling of emotion and speaker information contained in the acoustic features. The Interspeech ’09 Emotion Challenge feature set is used as the baseline for the audio part. A similar procedure is employed on the video signal, where the nuisance attribute projection (NAP) is used to derive the transformation matrix, which contains information about the emotional state of the speaker. Ultimately, different NAP transformation matrices are compared using canonical correlations. The audio and video sub-systems are combined at the matching score level using different fusion techniques. The presented system is assessed on the publicly available eNTERFACE’05 database where significant improvements in the recognition performance are observed when compared to the stat-of-the-art baseline.
Vitomir Štruc; Jerneja Žganec-Gros; Nikola Pavešić
Eye Localization using correlation filters Proceedings Article
V: Proceedings of the International Conference DOGS, str. 188-191, Novi Sad, Serbia, 2010.
@inproceedings{DOGS_Struc_2010,
title = {Eye Localization using correlation filters},
author = {Vitomir Štruc and Jerneja Žganec-Gros and Nikola Pavešić},
year = {2010},
date = {2010-01-01},
booktitle = {Proceedings of the International Conference DOGS},
pages = {188-191},
address = {Novi Sad, Serbia},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2009
Journal Articles
Vitomir Štruc; Nikola Pavešić
Gabor-based kernel-partial-least-squares discrimination features for face recognition Članek v strokovni reviji
V: Informatica (Vilnius), vol. 20, no. 1, str. 115-138, 2009.
@article{Inform-Struc_2009,
title = {Gabor-based kernel-partial-least-squares discrimination features for face recognition},
author = {Vitomir Štruc and Nikola Pavešić},
url = {https://lmi.fe.uni-lj.si/en/gabor-basedkernel-partial-least-squaresdiscriminationfeaturesforfacerecognition/},
year = {2009},
date = {2009-01-01},
urldate = {2009-01-01},
journal = {Informatica (Vilnius)},
volume = {20},
number = {1},
pages = {115-138},
abstract = {The paper presents a novel method for the extraction of facial features based on the Gabor-wavelet representation of face images and the kernel partial-least-squares discrimination (KPLSD) algorithm. The proposed feature-extraction method, called the Gabor-based kernel partial-least-squares discrimination (GKPLSD), is performed in two consecutive steps. In the first step a set of forty Gabor wavelets is used to extract discriminative and robust facial features, while in the second step the kernel partial-least-squares discrimination technique is used to reduce the dimensionality of the Gabor feature vector and to further enhance its discriminatory power. For optimal performance, the KPLSD-based transformation is implemented using the recently proposed fractional-power-polynomial models. The experimental results based on the XM2VTS and ORL databases show that the GKPLSD approach outperforms feature-extraction methods such as principal component analysis (PCA), linear discriminant analysis (LDA), kernel principal component analysis (KPCA) or generalized discriminant analysis (GDA) as well as combinations of these methods with Gabor representations of the face images. Furthermore, as the KPLSD algorithm is derived from the kernel partial-least-squares regression (KPLSR) model it does not suffer from the small-sample-size problem, which is regularly encountered in the field of face recognition.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The paper presents a novel method for the extraction of facial features based on the Gabor-wavelet representation of face images and the kernel partial-least-squares discrimination (KPLSD) algorithm. The proposed feature-extraction method, called the Gabor-based kernel partial-least-squares discrimination (GKPLSD), is performed in two consecutive steps. In the first step a set of forty Gabor wavelets is used to extract discriminative and robust facial features, while in the second step the kernel partial-least-squares discrimination technique is used to reduce the dimensionality of the Gabor feature vector and to further enhance its discriminatory power. For optimal performance, the KPLSD-based transformation is implemented using the recently proposed fractional-power-polynomial models. The experimental results based on the XM2VTS and ORL databases show that the GKPLSD approach outperforms feature-extraction methods such as principal component analysis (PCA), linear discriminant analysis (LDA), kernel principal component analysis (KPCA) or generalized discriminant analysis (GDA) as well as combinations of these methods with Gabor representations of the face images. Furthermore, as the KPLSD algorithm is derived from the kernel partial-least-squares regression (KPLSR) model it does not suffer from the small-sample-size problem, which is regularly encountered in the field of face recognition.
Vitomir Štruc; Janez Žibert; Nikola Pavešić
Histogram remapping as a preprocessing step for robust face recognition Članek v strokovni reviji
V: WSEAS transactions on information science and applications, vol. 6, no. 3, str. 520-529, 2009.
@article{WSEAS-Struc_2009,
title = {Histogram remapping as a preprocessing step for robust face recognition},
author = {Vitomir Štruc and Janez Žibert and Nikola Pavešić},
url = {https://lmi.fe.uni-lj.si/en/histogramremappingasapreprocessingstepforrobustfacerecognition/},
year = {2009},
date = {2009-01-01},
urldate = {2009-01-01},
journal = {WSEAS transactions on information science and applications},
volume = {6},
number = {3},
pages = {520-529},
abstract = {Image preprocessing techniques represent an essential part of a face recognition systems, which has a great impact on the performance and robustness of the recognition procedure. Amongst the number of techniques already presented in the literature, histogram equalization has emerged as the dominant preprocessing technique and is regularly used for the task of face recognition. With the property of increasing the global contrast of the facial image while simultaneously compensating for the illumination conditions present at the image acquisition stage, it represents a useful preprocessing step, which can ensure enhanced and more robust recognition performance. Even though, more elaborate normalization techniques, such as the multiscale retinex technique, isotropic and anisotropic smoothing, have been introduced to field of face recognition, they have been found to be more of a complement than a real substitute for histogram equalization. However, by closer examining the characteristics of histogram equalization, one can quickly discover that it represents only a specific case of a more general concept of histogram remapping techniques (which may have similar characteristics as histogram equalization does). While histogram equalization remapps the histogram of a given facial image to a uniform distribution, the target distribution could easily be replaced with an arbitrary one. As there is no theoretical justification of why the uniform distribution should be preferred to other target distributions, the question arises: how do other (non-uniform) target distributions influence the face recognition process and are they better suited for the recognition task. To tackle this issues, we present in this paper an empirical assessment of the concept of histogram remapping with the following target distributions: the uniform, the normal, the lognormal and the exponential distribution. We perform comparative experiments on the publicly available XM2VTS and YaleB databases and conclude that similar or even better recognition results that those ensured by histogram equalization can be achieved when other (non-uniform) target distribution are considered for the histogram remapping. This enhanced performance, however, comes at a price, as the nonuniform distributions rely on some parameters which have to be trained or selected appropriately to achieve the optimal performance.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Image preprocessing techniques represent an essential part of a face recognition systems, which has a great impact on the performance and robustness of the recognition procedure. Amongst the number of techniques already presented in the literature, histogram equalization has emerged as the dominant preprocessing technique and is regularly used for the task of face recognition. With the property of increasing the global contrast of the facial image while simultaneously compensating for the illumination conditions present at the image acquisition stage, it represents a useful preprocessing step, which can ensure enhanced and more robust recognition performance. Even though, more elaborate normalization techniques, such as the multiscale retinex technique, isotropic and anisotropic smoothing, have been introduced to field of face recognition, they have been found to be more of a complement than a real substitute for histogram equalization. However, by closer examining the characteristics of histogram equalization, one can quickly discover that it represents only a specific case of a more general concept of histogram remapping techniques (which may have similar characteristics as histogram equalization does). While histogram equalization remapps the histogram of a given facial image to a uniform distribution, the target distribution could easily be replaced with an arbitrary one. As there is no theoretical justification of why the uniform distribution should be preferred to other target distributions, the question arises: how do other (non-uniform) target distributions influence the face recognition process and are they better suited for the recognition task. To tackle this issues, we present in this paper an empirical assessment of the concept of histogram remapping with the following target distributions: the uniform, the normal, the lognormal and the exponential distribution. We perform comparative experiments on the publicly available XM2VTS and YaleB databases and conclude that similar or even better recognition results that those ensured by histogram equalization can be achieved when other (non-uniform) target distribution are considered for the histogram remapping. This enhanced performance, however, comes at a price, as the nonuniform distributions rely on some parameters which have to be trained or selected appropriately to achieve the optimal performance.
Rok Gajšek; Vitomir Štruc; France Mihelič; Anja Podlesek; Luka Komidar; Gregor Sočan; Boštjan Bajec
Multi-modal emotional database: AvID Članek v strokovni reviji
V: Informatica (Ljubljana), vol. 33, no. 1, str. 101-106, 2009.
@article{Inform-Gajsek_2009,
title = {Multi-modal emotional database: AvID},
author = {Rok Gajšek and Vitomir Štruc and France Mihelič and Anja Podlesek and Luka Komidar and Gregor Sočan and Boštjan Bajec},
url = {https://lmi.fe.uni-lj.si/en/multi-modalemotionaldatabaseavid/},
year = {2009},
date = {2009-01-01},
urldate = {2009-01-01},
journal = {Informatica (Ljubljana)},
volume = {33},
number = {1},
pages = {101-106},
abstract = {This paper presents our work on recording a multi-modal database containing emotional audio and video recordings. In designing the recording strategies a special attention was payed to gather data involving spontaneous emotions and therefore obtain a more realistic training and testing conditions for experiments. With specially planned scenarios including playing computer games and conducting an adaptive intelligence test different levels of arousal were induced. This will enable us to both detect different emotional states as well as experiment in speaker identification/verification of people involved in communications. So far the multi-modal database has been recorded and basic evaluation of the data was processed.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This paper presents our work on recording a multi-modal database containing emotional audio and video recordings. In designing the recording strategies a special attention was payed to gather data involving spontaneous emotions and therefore obtain a more realistic training and testing conditions for experiments. With specially planned scenarios including playing computer games and conducting an adaptive intelligence test different levels of arousal were induced. This will enable us to both detect different emotional states as well as experiment in speaker identification/verification of people involved in communications. So far the multi-modal database has been recorded and basic evaluation of the data was processed.
Vitomir Štruc; Rok Gajšek; France Mihelič; Nikola Pavešić
Using regression techniques for coping with the one-sample-size problem of face recognition Članek v strokovni reviji
V: Electrotechnical Review, vol. 76, no. 1-2, str. 7-12, 2009.
@article{EV-Struc_2009,
title = {Using regression techniques for coping with the one-sample-size problem of face recognition},
author = {Vitomir Štruc and Rok Gajšek and France Mihelič and Nikola Pavešić},
url = {https://lmi.fe.uni-lj.si/en/usingregressiontechniquesforcopingwiththeone-sample-sizeproblemoffacerecognition/},
year = {2009},
date = {2009-01-01},
urldate = {2009-01-01},
journal = {Electrotechnical Review},
volume = {76},
number = {1-2},
pages = {7-12},
abstract = {There is a number of face recognition paradigms which ensure good recognition rates with frontal face images. However, the majority of them require an extensive training set and degrade in their performance when an insufficient number of training images is available. This is especially true for applications where only one image per subject is at hand for training. To cope with this one-sample-size (OSS) problem, we propose to employ subspace projection based regression techniques rather than modifications of the established face recognition paradigms, such as the principal component or linear discriminant analysis, as it was done in the past. Experiments performed on the XM2VTS and ORL databases show the effectiveness of the proposed approach. Also presented is a comparative assessment of several regression techniques and some popular face
recognition methods.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
There is a number of face recognition paradigms which ensure good recognition rates with frontal face images. However, the majority of them require an extensive training set and degrade in their performance when an insufficient number of training images is available. This is especially true for applications where only one image per subject is at hand for training. To cope with this one-sample-size (OSS) problem, we propose to employ subspace projection based regression techniques rather than modifications of the established face recognition paradigms, such as the principal component or linear discriminant analysis, as it was done in the past. Experiments performed on the XM2VTS and ORL databases show the effectiveness of the proposed approach. Also presented is a comparative assessment of several regression techniques and some popular face
recognition methods.
recognition methods.
Vitomir Štruc; Nikola Pavešić
Phase-congruency features for palm-print verification Članek v strokovni reviji
V: IET Signal Processing, vol. 3, no. 4, str. 258-268, 2009.
@article{IET-Struc_2009,
title = {Phase-congruency features for palm-print verification},
author = {Vitomir Štruc and Nikola Pavešić},
url = {https://lmi.fe.uni-lj.si/en/phase-congruencyfeaturesforpalm-printverification/},
doi = {10.1049/iet-spr.2008.0152},
year = {2009},
date = {2009-01-01},
urldate = {2009-01-01},
journal = {IET Signal Processing},
volume = {3},
number = {4},
pages = {258-268},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Vitomir Štruc; Nikola Pavešić
Gaussianization of image patches for efficient palmprint recognition Članek v strokovni reviji
V: Electrotechnical Review, vol. 76, no. 5, str. 245-250, 2009.
@article{EV_2009_palms,
title = {Gaussianization of image patches for efficient palmprint recognition},
author = {Vitomir Štruc and Nikola Pavešić},
url = {https://lmi.fe.uni-lj.si/en/gaussianizationofimagepatchesforefficientpalmprintrecognition/},
year = {2009},
date = {2009-01-01},
urldate = {2009-01-01},
journal = {Electrotechnical Review},
volume = {76},
number = {5},
pages = {245-250},
abstract = {In this paper we present a comparison of the two dominant image preprocessing techniques for palmprint recognition, namely, histogram equalization and mean-variance normalization. We show that both techniques pursue a similar goal and that the difference in recognition efficiency stems from the fact that not all assumptions underlying the mean-variance normalization approach are always met. We present an alternative justification of why histogram equalization ensures enhanced verification performance, and, based on the findings, propose two novel preprocessing techniques: gaussianization of the palmprint images and gaussianization of image patches. We present comparative results obtained on the PolyU database and show that the patch-based normalization technique ensures stat-of-the-art recognition results with a simple feature extraction method and the nearest neighbor classifier.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In this paper we present a comparison of the two dominant image preprocessing techniques for palmprint recognition, namely, histogram equalization and mean-variance normalization. We show that both techniques pursue a similar goal and that the difference in recognition efficiency stems from the fact that not all assumptions underlying the mean-variance normalization approach are always met. We present an alternative justification of why histogram equalization ensures enhanced verification performance, and, based on the findings, propose two novel preprocessing techniques: gaussianization of the palmprint images and gaussianization of image patches. We present comparative results obtained on the PolyU database and show that the patch-based normalization technique ensures stat-of-the-art recognition results with a simple feature extraction method and the nearest neighbor classifier.
Blaž Stres; James M Tiedje; Boštjan Murovec
BEsTRF: a tool for optimal resolution of terminal-restriction fragment length polymorphism analysis based on user-defined primer–enzyme–sequence databases Članek v strokovni reviji
V: Bioinformatics, vol. 25, no. 12, str. 1556-1558, 2009, ISSN: 1367-4803.
@article{10.1093/bioinformatics/btp254,
title = {BEsTRF: a tool for optimal resolution of terminal-restriction fragment length polymorphism analysis based on user-defined primer–enzyme–sequence databases},
author = {Blaž Stres and James M Tiedje and Boštjan Murovec},
url = {https://doi.org/10.1093/bioinformatics/btp254},
doi = {10.1093/bioinformatics/btp254},
issn = {1367-4803},
year = {2009},
date = {2009-01-01},
journal = {Bioinformatics},
volume = {25},
number = {12},
pages = {1556-1558},
abstract = {Summary: BEsTRF (Best Estimated T-RF) provides a standalone environment for analyzing primers-enzymes-gene section combinations used in terminal-restriction fragment length polymorphism (T-RFLP) for its optimal resolution. User-defined sequence databases of several hundred thousand DNA sequences can be explored and the resolution of user-specified sets of primers and restriction endonucleases can be analyzed on either forward or reverse terminal fragments. Sequence quality, primer mismatches, insertions and deletions can be controlled and each primer pair-specific sequence collections can be exported for downstream analyses. The configuration for a novel T-RFLP population profiling using rpoB gene (DNA-directed RNA polymerase, beta subunit) on forward fluorescently labeled primer are presented.Availability: BEsTRF is freely available at http://lie.fe.uni-lj.si/bestrf and can be downloaded from the same site. The online protocol, numerous primer and enzyme dictionaries, sequence collections and results generated during this work for various genes are available at our website http://lie.fe.uni-lj.si/bestrf.Contact:blaz.stres@bfro.uni-lj.si},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Summary: BEsTRF (Best Estimated T-RF) provides a standalone environment for analyzing primers-enzymes-gene section combinations used in terminal-restriction fragment length polymorphism (T-RFLP) for its optimal resolution. User-defined sequence databases of several hundred thousand DNA sequences can be explored and the resolution of user-specified sets of primers and restriction endonucleases can be analyzed on either forward or reverse terminal fragments. Sequence quality, primer mismatches, insertions and deletions can be controlled and each primer pair-specific sequence collections can be exported for downstream analyses. The configuration for a novel T-RFLP population profiling using rpoB gene (DNA-directed RNA polymerase, beta subunit) on forward fluorescently labeled primer are presented.Availability: BEsTRF is freely available at http://lie.fe.uni-lj.si/bestrf and can be downloaded from the same site. The online protocol, numerous primer and enzyme dictionaries, sequence collections and results generated during this work for various genes are available at our website http://lie.fe.uni-lj.si/bestrf.Contact:blaz.stres@bfro.uni-lj.si
Book Sections
Vitomir Štruc; Nikola Pavešić
Hand-Geometry Device Book Section
V: Li, Stan Z (Ur.): Encyclopedia of biometrics, str. 693-698, Springer-Verlag, New York, 2009.
@incollection{Springer2009,
title = {Hand-Geometry Device},
author = {Vitomir Štruc and Nikola Pavešić},
editor = {Stan Z Li},
url = {https://lmi.fe.uni-lj.si/en/hand-geometrydevice/},
doi = {10.1007/978-0-387-73003-5_14},
year = {2009},
date = {2009-01-01},
urldate = {2009-01-01},
booktitle = {Encyclopedia of biometrics},
pages = {693-698},
publisher = {Springer-Verlag},
address = {New York},
abstract = {Hand-geometry devices are specially designed biometric devices used for capturing the geometric characteristics (e.g., the length, width, thickness and curvature of the fingers, the palm size, and the distances between joints) of a human hand for hand-geometry-based identity verification. A typical hand-geometry device records images of the lateral and dorsal parts of the hand with a charge-coupled device (CCD) camera that is mounted above a flat surface on which the person presented to the device places his/her hand. The set of geometrical features extracted from these images is then matched against a pre-recorded template stored in the device’s database. Depending on the result of this matching procedure, the identity of the person presented to the device is either verified or not.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Hand-geometry devices are specially designed biometric devices used for capturing the geometric characteristics (e.g., the length, width, thickness and curvature of the fingers, the palm size, and the distances between joints) of a human hand for hand-geometry-based identity verification. A typical hand-geometry device records images of the lateral and dorsal parts of the hand with a charge-coupled device (CCD) camera that is mounted above a flat surface on which the person presented to the device places his/her hand. The set of geometrical features extracted from these images is then matched against a pre-recorded template stored in the device’s database. Depending on the result of this matching procedure, the identity of the person presented to the device is either verified or not.
Proceedings Articles
Vitomir Štruc; Rok Gajšek; Nikola Pavešić
Principal Gabor Filters for Face Recognition Proceedings Article
V: Proceedings of the 3rd IEEE International Conference on Biometrics: Theory, Systems and Applications (BTAS'09), str. 1-6, IEEE, Washington D.C., U.S.A., 2009.
@inproceedings{BTAS2009,
title = {Principal Gabor Filters for Face Recognition},
author = {Vitomir Štruc and Rok Gajšek and Nikola Pavešić},
url = {https://lmi.fe.uni-lj.si/en/principalgaborfiltersforfacerecognition/},
doi = {10.1109/BTAS.2009.5339020},
year = {2009},
date = {2009-09-01},
urldate = {2009-09-01},
booktitle = {Proceedings of the 3rd IEEE International Conference on Biometrics: Theory, Systems and Applications (BTAS'09)},
pages = {1-6},
publisher = {IEEE},
address = {Washington D.C., U.S.A.},
abstract = {Gabor filters have proven themselves to be a powerful tool for facial feature extraction. An abundance of recognition techniques presented in the literature exploits these filters to achieve robust face recognition. However, while exhibiting desirable properties, such as orientational selectivity or spatial locality, Gabor filters have also some shortcomings which crucially affect the characteristics and size of the Gabor representation of a given face pattern. Amongst these shortcomings the fact that the filters are not orthogonal one to another and are, hence, correlated is probably the most important. This makes the information contained in the Gabor face representation redundant and also affects the size of the representation. To overcome this problem we propose in this paper to employ orthonormal linear combinations of the original Gabor filters rather than the filters themselves for deriving the Gabor face representation. The filters, named principal Gabor filters for the fact that they are computed by means of principal component analysis, are assessed in face recognition experiments performed on the XM2VTS and YaleB databases, where encouraging results are achieved.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Gabor filters have proven themselves to be a powerful tool for facial feature extraction. An abundance of recognition techniques presented in the literature exploits these filters to achieve robust face recognition. However, while exhibiting desirable properties, such as orientational selectivity or spatial locality, Gabor filters have also some shortcomings which crucially affect the characteristics and size of the Gabor representation of a given face pattern. Amongst these shortcomings the fact that the filters are not orthogonal one to another and are, hence, correlated is probably the most important. This makes the information contained in the Gabor face representation redundant and also affects the size of the representation. To overcome this problem we propose in this paper to employ orthonormal linear combinations of the original Gabor filters rather than the filters themselves for deriving the Gabor face representation. The filters, named principal Gabor filters for the fact that they are computed by means of principal component analysis, are assessed in face recognition experiments performed on the XM2VTS and YaleB databases, where encouraging results are achieved.
Rok Gajšek; Vitomir Štruc; Simon Dobrišek; France Mihelič
Emotion recognition using linear transformations in combination with video Proceedings Article
V: Speech and intelligence: proceedings of Interspeech 2009, str. 1967-1970, Brighton, UK, 2009.
@inproceedings{InterSp2009,
title = {Emotion recognition using linear transformations in combination with video},
author = {Rok Gajšek and Vitomir Štruc and Simon Dobrišek and France Mihelič},
url = {https://lmi.fe.uni-lj.si/en/emotionrecognitionusinglineartransformationsincombinationwithvideo/},
year = {2009},
date = {2009-09-01},
urldate = {2009-09-01},
booktitle = {Speech and intelligence: proceedings of Interspeech 2009},
pages = {1967-1970},
address = {Brighton, UK},
abstract = {The paper discuses the usage of linear transformations of Hidden Markov Models, normally employed for speaker and environment adaptation, as a way of extracting the emotional components from the speech. A constrained version of Maximum Likelihood Linear Regression (CMLLR) transformation is used as a feature for classification of normal or aroused emotional state. We present a procedure of incrementally building a set of speaker independent acoustic models, that are used to estimate the CMLLR transformations for emotion classification. An audio-video database of spontaneous emotions (AvID) is briefly presented since it forms the basis for the evaluation of the proposed method. Emotion classification using the video part of the database is also described and the added value of combining the visual information with the audio features is shown.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The paper discuses the usage of linear transformations of Hidden Markov Models, normally employed for speaker and environment adaptation, as a way of extracting the emotional components from the speech. A constrained version of Maximum Likelihood Linear Regression (CMLLR) transformation is used as a feature for classification of normal or aroused emotional state. We present a procedure of incrementally building a set of speaker independent acoustic models, that are used to estimate the CMLLR transformations for emotion classification. An audio-video database of spontaneous emotions (AvID) is briefly presented since it forms the basis for the evaluation of the proposed method. Emotion classification using the video part of the database is also described and the added value of combining the visual information with the audio features is shown.
Vitomir Štruc; Zongmin Ma; Nikola Pavešić
Nuisance Attribute Projection in the Logarithm Domain for Face Recognition under Severe Illumination Changes Proceedings Article
V: Proceedings of the IEEE International Electrotechnical and Computer Science Conference (ERK'09), str. 279-281, Portorož, Slovenia, 2009.
@inproceedings{ERK2009N,
title = {Nuisance Attribute Projection in the Logarithm Domain for Face Recognition under Severe Illumination Changes},
author = {Vitomir Štruc and Zongmin Ma and Nikola Pavešić},
year = {2009},
date = {2009-09-01},
booktitle = {Proceedings of the IEEE International Electrotechnical and Computer Science Conference (ERK'09)},
pages = {279-281},
address = {Portorož, Slovenia},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Vitomir Štruc; Zongmin Ma; Nikola Pavešić
Face Recognition using Sparse Projection Axes Proceedings Article
V: Proceedings of the IEEE International Electrotechnical and Computer Science Conference (ERK'09), str. 271-274, Portorož, Slovenia, 2009.
@inproceedings{ERK2009S,
title = {Face Recognition using Sparse Projection Axes},
author = {Vitomir Štruc and Zongmin Ma and Nikola Pavešić},
year = {2009},
date = {2009-09-01},
booktitle = {Proceedings of the IEEE International Electrotechnical and Computer Science Conference (ERK'09)},
pages = {271-274},
address = {Portorož, Slovenia},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Vitomir Štruc; Nikola Pavešić
A comparative assessment of appearance based feature extraction techniques and their susceptibility to image degradations in face recognition systems Proceedings Article
V: Proceedings of the International Conference on Machine Learning and Pattern Recognition (ICMLPR'09), str. 326-334, Paris, France, 2009.
@inproceedings{FSKD208b,
title = {A comparative assessment of appearance based feature extraction techniques and their susceptibility to image degradations in face recognition systems},
author = {Vitomir Štruc and Nikola Pavešić},
url = {https://lmi.fe.uni-lj.si/en/acomparativeassessmentofappearancebasedfeatureextractiontechniquesandtheirsusceptibilitytoimagedegradationsinfacerecognitionsystems/},
year = {2009},
date = {2009-06-01},
urldate = {2009-06-01},
booktitle = {Proceedings of the International Conference on Machine Learning and Pattern Recognition (ICMLPR'09)},
volume = {54},
pages = {326-334},
address = {Paris, France},
abstract = {Over the past decades, automatic face recognition has become a highly active research area, mainly due to the countless application possibilities in both the private as well as the public sector. Numerous algorithms have been proposed in the literature to cope with the problem of face recognition, nevertheless, a group of methods commonly referred to as appearance based have emerged as the dominant solution to the face recognition problem. Many comparative studies concerned with the performance of appearance based methods have already been presented in the literature, not rarely with inconclusive and often with contradictory results. No consent has been reached within the scientific community regarding the relative ranking of the efficiency of appearance based methods for the face recognition task, let alone regarding their susceptibility to appearance changes induced by various environmental factors. To tackle these open issues, this paper assess the performance of the three dominant appearance based methods: principal component analysis, linear discriminant analysis and independent component analysis, and compares them on equal footing (i.e., with the same preprocessing procedure, with optimized parameters for the best possible performance, etc.) in face verification experiments on the publicly available XM2VTS database. In addition to the comparative analysis on the XM2VTS database, ten degraded versions of the database are also employed in the experiments to evaluate the susceptibility of the appearance based methods on various image degradations which can occur in ”real-life” operating conditions. Our experimental results suggest that linear discriminant analysis ensures the most consistent verification rates across the tested databases.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Over the past decades, automatic face recognition has become a highly active research area, mainly due to the countless application possibilities in both the private as well as the public sector. Numerous algorithms have been proposed in the literature to cope with the problem of face recognition, nevertheless, a group of methods commonly referred to as appearance based have emerged as the dominant solution to the face recognition problem. Many comparative studies concerned with the performance of appearance based methods have already been presented in the literature, not rarely with inconclusive and often with contradictory results. No consent has been reached within the scientific community regarding the relative ranking of the efficiency of appearance based methods for the face recognition task, let alone regarding their susceptibility to appearance changes induced by various environmental factors. To tackle these open issues, this paper assess the performance of the three dominant appearance based methods: principal component analysis, linear discriminant analysis and independent component analysis, and compares them on equal footing (i.e., with the same preprocessing procedure, with optimized parameters for the best possible performance, etc.) in face verification experiments on the publicly available XM2VTS database. In addition to the comparative analysis on the XM2VTS database, ten degraded versions of the database are also employed in the experiments to evaluate the susceptibility of the appearance based methods on various image degradations which can occur in ”real-life” operating conditions. Our experimental results suggest that linear discriminant analysis ensures the most consistent verification rates across the tested databases.
Vitomir Štruc; Nikola Pavešić
A comparison of feature normalization techniques for PCA-based palmprint recognition Proceedings Article
V: Proceedings of the International Conference on Mathematical Modeling (MATHMOD'09), str. 2450-2453, Viena, Austria, 2009.
@inproceedings{Mathmod09,
title = {A comparison of feature normalization techniques for PCA-based palmprint recognition},
author = {Vitomir Štruc and Nikola Pavešić},
url = {https://lmi.fe.uni-lj.si/en/acomparisonoffeaturenormalizationtechniquesforpca-basedpalmprintrecognition/},
year = {2009},
date = {2009-02-01},
urldate = {2009-02-01},
booktitle = {Proceedings of the International Conference on Mathematical Modeling (MATHMOD'09)},
pages = {2450-2453},
address = {Viena, Austria},
abstract = {Computing user templates (or models) for biometric authentication systems is one of the most crucial steps towards efficient and accurate biometric recognition. The constructed templates should encode user specific information extracted from a sample of a given biometric modality, such as, for example, palmprints, and exhibit a sufficient level of dissimilarity with other templates stored in the systems database. Clearly, the characteristics of the user templates depend on the approach employed for the extraction of biometric features, as well as on the procedure used to normalize the extracted feature vectors. While feature-extraction methods are a well studied topic, for which a vast amount of comparative studies can be found in the literature, normalization techniques lack such studies and are only briefly mentioned in most cases. In this paper we, therefore, apply several normalization techniques to feature vectors extracted from palmprint images by means of principal component analysis (PCA) and perform a comparative analysis on the results. We show that the choice of an appropriate normalization technique greatly influences the performance of the palmprint-based authentication system and can result in error rate reductions of more than 30%.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Computing user templates (or models) for biometric authentication systems is one of the most crucial steps towards efficient and accurate biometric recognition. The constructed templates should encode user specific information extracted from a sample of a given biometric modality, such as, for example, palmprints, and exhibit a sufficient level of dissimilarity with other templates stored in the systems database. Clearly, the characteristics of the user templates depend on the approach employed for the extraction of biometric features, as well as on the procedure used to normalize the extracted feature vectors. While feature-extraction methods are a well studied topic, for which a vast amount of comparative studies can be found in the literature, normalization techniques lack such studies and are only briefly mentioned in most cases. In this paper we, therefore, apply several normalization techniques to feature vectors extracted from palmprint images by means of principal component analysis (PCA) and perform a comparative analysis on the results. We show that the choice of an appropriate normalization technique greatly influences the performance of the palmprint-based authentication system and can result in error rate reductions of more than 30%.
Vitomir Štruc; Nikola Pavešić
Image normalization techniques for robust face recognition Proceedings Article
V: Proceedings of the International Conference on Signal Processing, Robotics and Automation (ISPRA'09), str. 155-160, Cambridge, UK, 2009.
@inproceedings{ISPRA09,
title = {Image normalization techniques for robust face recognition},
author = {Vitomir Štruc and Nikola Pavešić},
year = {2009},
date = {2009-02-01},
booktitle = {Proceedings of the International Conference on Signal Processing, Robotics and Automation (ISPRA'09)},
pages = {155-160},
address = {Cambridge, UK},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}