Objave

@inproceedings{Babnik_IWBF2024,

title = {AI-KD: Towards Alignment Invariant Face Image Quality Assessment Using Knowledge Distillation},

author = {Žiga Babnik and Fadi Boutros and Naser Damer and Peter Peer and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2024/03/iwbf2024_fiq.pdf},

year  = {2024},

date = {2024-04-10},

urldate = {2024-04-10},

booktitle = {Proceedings of the International Workshop on Biometrics and Forensics (IWBF)},

pages = {1-6},

abstract = {Face Image Quality Assessment (FIQA) techniques have seen steady improvements over recent years, but their performance still deteriorates if the input face samples are not properly aligned. This alignment sensitivity comes from the fact that most FIQA techniques are trained or designed using a specific face alignment procedure. If the alignment technique changes, the performance of most existing FIQA techniques quickly becomes suboptimal. To address this problem, we present in this paper a novel knowledge distillation approach, termed AI-KD that can extend on any existing FIQA technique, improving its robustness to alignment variations and, in turn, performance with different alignment procedures. To validate the proposed distillation approach, we conduct comprehensive experiments on 6 face datasets with 4 recent face recognition models and in comparison to 7 state-of-the-art FIQA techniques. Our results show that AI-KD consistently improves performance of the initial FIQA techniques not only with misaligned samples, but also with properly aligned facial images. Furthermore, it leads to a new state-of-the-art, when used with a competitive initial FIQA approach. The code for AI-KD is made publicly available from: https://github.com/LSIbabnikz/AI-KD.},

keywords = {ai, CNN, deep learning, face, face image quality assessment, face image quality estimation, face images, face recognition, face verification},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Diffiqa_2023,

title = {DifFIQA: Face Image Quality Assessment Using Denoising Diffusion Probabilistic Models},

author = {Žiga Babnik and Peter Peer and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2023/09/121.pdf

https://lmi.fe.uni-lj.si/wp-content/uploads/2023/09/121-supp.pdf},

year  = {2023},

date = {2023-09-01},

booktitle = {IEEE International Joint Conference on Biometrics },

pages = {1-10},

publisher = {IEEE},

address = {Ljubljana, Slovenia},

abstract = {Modern face recognition (FR) models excel in constrained

scenarios, but often suffer from decreased performance

when deployed in unconstrained (real-world) environments

due to uncertainties surrounding the quality

of the captured facial data. Face image quality assessment

(FIQA) techniques aim to mitigate these performance

degradations by providing FR models with sample-quality

predictions that can be used to reject low-quality samples

and reduce false match errors. However, despite steady improvements,

ensuring reliable quality estimates across facial

images with diverse characteristics remains challenging.

In this paper, we present a powerful new FIQA approach,

named DifFIQA, which relies on denoising diffusion

probabilistic models (DDPM) and ensures highly competitive

results. The main idea behind the approach is to utilize

the forward and backward processes of DDPMs to perturb

facial images and quantify the impact of these perturbations

on the corresponding image embeddings for quality

prediction. Because the diffusion-based perturbations are

computationally expensive, we also distill the knowledge

encoded in DifFIQA into a regression-based quality predictor,

called DifFIQA(R), that balances performance and

execution time. We evaluate both models in comprehensive

experiments on 7 diverse datasets, with 4 target FR models

and against 10 state-of-the-art FIQA techniques with

highly encouraging results. The source code is available

from: https://github.com/LSIbabnikz/DifFIQA.},

keywords = {biometrics, deep learning, denoising diffusion probabilistic models, diffusion, face, face image quality assesment, face recognition, FIQA, quality},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{EFAR2023_2023,

title = {EFaR 2023: Efficient Face Recognition Competition},

author = {Jan Niklas Kolf and Fadi Boutros and Jurek Elliesen and Markus Theuerkauf and Naser Damer and Mohamad Y Alansari and Oussama Abdul Hay and Sara Yousif Alansari and Sajid Javed and Naoufel Werghi and Klemen Grm and Vitomir Struc and Fernando Alonso-Fernandez and Kevin Hernandez-Diaz and Josef Bigun and Anjith George and Christophe Ecabert and Hatef Otroshi Shahreza and Ketan Kotwal and Sébastien Marcel and Iurii Medvedev and Jin Bo and Diogo Nunes and Ahmad Hassanpour and Pankaj Khatiwada and Aafan Ahmad Toor and Bian Yang},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2023/09/CameraReady-231.pdf},

year  = {2023},

date = {2023-09-01},

booktitle = {IEEE International Joint Conference on Biometrics (IJCB 2023)},

pages = {1-12},

address = {Ljubljana, Slovenia},

abstract = {This paper presents the summary of the Efficient Face

Recognition Competition (EFaR) held at the 2023 International

Joint Conference on Biometrics (IJCB 2023). The

competition received 17 submissions from 6 different teams.

To drive further development of efficient face recognition

models, the submitted solutions are ranked based on a

weighted score of the achieved verification accuracies on a

diverse set of benchmarks, as well as the deployability given

by the number of floating-point operations and model size.

The evaluation of submissions is extended to bias, crossquality,

and large-scale recognition benchmarks. Overall,

the paper gives an overview of the achieved performance

values of the submitted solutions as well as a diverse set of

baselines. The submitted solutions use small, efficient network

architectures to reduce the computational cost, some

solutions apply model quantization. An outlook on possible

techniques that are underrepresented in current solutions is

given as well.},

keywords = {biometrics, deep learning, face, face recognition, lightweight models},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{WACVW2023,

title = {Meet-in-the-middle: Multi-scale upsampling and matching for cross-resolution face recognition},

author = {Klemen Grm and Berk Ozata and Vitomir Struc and Hazim K. Ekenel},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2023/01/Meet_in_the_middle.pdf

https://arxiv.org/abs/2211.15225

https://openaccess.thecvf.com/content/WACV2023W/RWS/papers/Grm_Meet-in-the-Middle_Multi-Scale_Upsampling_and_Matching_for_Cross-Resolution_Face_Recognition_WACVW_2023_paper.pdf



},

year  = {2023},

date = {2023-01-06},

booktitle = {WACV workshops},

pages = {120-129},

abstract = {In this paper, we aim to address the large domain gap between high-resolution face images, e.g., from professional portrait photography, and low-quality surveillance images, e.g., from security cameras. Establishing an identity match between disparate sources like this is a classical surveillance face identification scenario, which continues to be a challenging problem for modern face recognition techniques. To that end, we propose a method that combines face super-resolution, resolution matching, and multi-scale template accumulation to reliably recognize faces from long-range surveillance footage, including from low quality sources. The proposed approach does not require training or fine-tuning on the target dataset of real surveillance images. Extensive experiments show that our proposed method is able to outperform even existing methods fine-tuned to the SCFace dataset.},

keywords = {deep learning, face, face recognition, multi-scale matching, smart surveillance, surveillance, surveillance technology},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{BabnikErk2022,

title = {Iterativna optimizacija ocen kakovosti slikovnih podatkov v sistemih za razpoznavanje obrazov},

author = {Žiga Babnik and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2022/08/ERK_2022.pdf},

year  = {2022},

date = {2022-08-01},

booktitle = {Proceedings of ERK 2022},

pages = {1-4},

abstract = {While recent face recognition (FR) systems achieve excellent results in many deployment scenarios, their performance in challenging real-world settings is still under question. For this reason, face image quality assessment (FIQA) techniques aim to support FR systems, by providing them with sample quality information that can be used to reject poor quality data unsuitable for recognition purposes. Several groups of FIQA methods relying on different concepts have been proposed in the literature, all of which can be used for generating quality scores of facial images that can serve as pseudo ground-truth (quality) labels and be exploited for training (regression-based) quality estimation models. Several FIQA approaches show that a significant amount of sample-quality information can be extracted from mated similarity-score distributions generated with some face matcher. Based on this insight, we propose in this paper a quality label optimization approach, which incorporates sample-quality information from mated-pair similarities into quality predictions of existing off-the-shelf FIQA techniques. We evaluate the proposed approach using three state-of-the-art FIQA methods over three diverse datasets. The results of our experiments show that the proposed optimization procedure heavily depends on the number of executed optimization iterations. At ten iterations, the approach seems to perform the best, consistently outperforming the base quality scores of the three FIQA methods, chosen for the experiments.},

keywords = {CNN, face image quality estimation, face quality, face recognition, optimization, supervised quality estimation},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ICPR2022,

title = {FaceQAN: Face Image Quality Assessment Through Adversarial Noise Exploration},

author = {Žiga Babnik and Peter Peer and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2022/06/ICPR_2022___paper-17.pdf},

year  = {2022},

date = {2022-05-17},

urldate = {2022-05-17},

booktitle = {IAPR International Conference on Pattern Recognition (ICPR)},

abstract = {Recent state-of-the-art face recognition (FR) approaches have achieved impressive performance, yet unconstrained face recognition still represents an open problem. Face image quality assessment (FIQA) approaches aim to estimate the quality of the input samples that can help provide information on the confidence of the recognition decision and eventually lead to improved results in challenging scenarios. While much progress has been made in face image quality assessment in recent years, computing reliable quality scores for diverse facial images and FR models remains challenging. In this paper, we propose a novel approach to face image quality assessment, called FaceQAN, that is based on adversarial examples and relies on the analysis of adversarial noise which can be calculated with any FR model learned by using some form of gradient descent. As such, the proposed approach is the first to link image quality to adversarial attacks. Comprehensive (cross-model as well as model-specific) experiments are conducted with four benchmark datasets, i.e., LFW, CFP–FP, XQLFW and IJB–C, four FR models, i.e., CosFace, ArcFace, CurricularFace and ElasticFace and in comparison to seven state-of-the-art FIQA methods to demonstrate the performance of FaceQAN. Experimental results show that FaceQAN achieves competitive results, while exhibiting several desirable characteristics. The source code for FaceQAN will be made publicly available.},

keywords = {adversarial examples, adversarial noise, biometrics, face image quality assessment, face recognition, FIQA, image quality assessment},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{EUSIPCO_2022,

title = {Assessing Bias in Face Image Quality Assessment},

author = {Žiga Babnik and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2022/06/EUSIPCO_2022___paper.pdf},

year  = {2022},

date = {2022-05-16},

urldate = {2022-05-16},

booktitle = {EUSIPCO 2022},

abstract = {Face image quality assessment (FIQA) attempts to improve face recognition (FR) performance  by providing additional information about sample quality. 

Because FIQA methods attempt to estimate the utility of a sample for face recognition, it is reasonable to assume that these methods are heavily influenced by the underlying face recognition system. Although modern face recognition systems are known to perform well, several studies have found that such systems often exhibit problems with demographic bias. It is therefore likely that such problems are also present with FIQA techniques. To investigate the demographic biases associated with FIQA approaches, this paper presents a comprehensive study involving a variety of quality assessment methods (general-purpose image quality assessment, supervised face quality assessment, and unsupervised face quality assessment methods) and three diverse state-of-the-art FR models. 

Our analysis on the Balanced Faces in the Wild (BFW) dataset shows that all techniques considered are affected more by variations in race than sex. While the general-purpose image quality assessment methods appear to be less biased with respect to the two demographic factors considered, the supervised and unsupervised face image quality assessment methods both show strong bias with a tendency to favor white individuals (of either sex). In addition, we found that methods that are less racially biased perform worse overall. This suggests that the observed bias in FIQA methods is to a significant extent related to the underlying face recognition system.},

keywords = {bias, bias analysis, biometrics, face image quality assessment, face recognition, FIQA, image quality assessment},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{MFR_IJCB2021,

title = {MFR 2021: Masked Face Recognition Competition},

author = {Fadi Boutros and Naser Damer and Jan Niklas Kolf and Kiran Raja and Florian Kirchbuchner and Raghavendra Ramachandra and Arjan Kuijper and Pengcheng Fang and Chao Zhang and Fei Wang and David Montero and Naiara Aginako and Basilio Sierra and Marcos Nieto and Mustafa Ekrem Erakin and Ugur Demir and Hazım Kemal Ekenel and Asaki Kataoka and Kohei Ichikawa and Shizuma Kubo and Jie Zhang and Mingjie He and Dan Han and Shiguang Shan and Klemen Grm and Vitomir Štruc and Sachith Seneviratne and Nuran Kasthuriarachchi and Sanka Rasnayaka and Pedro C. Neto and Ana F. Sequeira and Joao Ribeiro Pinto and Mohsen Saffari and Jaime S. Cardoso},

url = {https://ieeexplore.ieee.org/iel7/9484326/9484328/09484337.pdf?casa_token=OOL4s274P0YAAAAA:XE7ga2rP_wNom2Zeva75ZwNwN-HKz6kF1HZtkpzrdTdz36eaGcLffWkzOgIe3xU2PqaU30qTLws},

doi = {10.1109/IJCB52358.2021.9484337},

year  = {2021},

date = {2021-08-01},

booktitle = {Proceedings of the IEEE International Joint Conference on Biometrics (IJCB 2021)},

abstract = {This paper presents a summary of the Masked Face Recognition Competitions (MFR) held within the 2021 International Joint Conference on Biometrics (IJCB 2021). The competition attracted a total of 10 participating teams with valid submissions. The affiliations of these teams are diverse and associated with academia and industry in nine different countries. These teams successfully submitted 18 valid solutions. The competition is designed to motivate solutions aiming at enhancing the face recognition accuracy of masked faces. Moreover, the competition considered the deployability of the proposed solutions by taking the compactness of the face recognition models into account. A private dataset representing a collaborative, multisession, real masked, capture scenario is used to evaluate the submitted solutions. In comparison to one of the topperforming academic face recognition solutions, 10 out of the 18 submitted solutions did score higher masked face verification accuracy.

},

keywords = {biometrics, face recognition, masks},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{BortolatoFG2020,

title = {Learning privacy-enhancing face representations through feature disentanglement},

author = {Blaž Bortolato and Marija Ivanovska and Peter Rot and Janez Križaj and Philipp Terhorst and Naser Damer and Peter Peer and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2020/07/FG2020___Learning_privacy_enhancing_face_representations_through_feature_disentanglement-1.pdf

},

year  = {2020},

date = {2020-11-04},

booktitle = {Proceedings of FG 2020},

publisher = {IEEE},

abstract = {Convolutional Neural Networks (CNNs) are today the de-facto standard for extracting compact and discriminative face representations (templates) from images in automatic face recognition systems. Due to the characteristics of CNN models, the generated representations typically encode a multitude of information ranging from identity to soft-biometric attributes, such as age, gender or ethnicity. However, since these representations were computed for the purpose of identity recognition only, the soft-biometric information contained in the templates represents a serious privacy risk. To mitigate this problem, we present in this paper a privacy-enhancing approach capable of suppressing potentially sensitive soft-biometric information in face representations without significantly compromising identity information. Specifically, we introduce a Privacy-Enhancing Face-Representation learning Network (PFRNet) that disentangles identity from attribute information in face representations and consequently allows to efficiently suppress soft-biometrics in face templates. We demonstrate the feasibility of PFRNet on the problem of gender suppression and show through rigorous experiments on the CelebA, Labeled Faces in the Wild (LFW) and Adience datasets that the proposed disentanglement-based approach is highly effective and improves significantly on the existing state-of-the-art.},

keywords = {autoencoder, biometrics, CNN, disentaglement, face recognition, PFRNet, privacy, representation learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Biosig_naser_2020,

title = {Privacy Evaluation Protocols for the Evaluation of Soft-Biometric Privacy-Enhancing Technologies},

author = {Philipp Terhörst, Marco Huber, Naser Damer, Peter Rot, Florian Kirchbuchner, Vitomir Struc, Arjan Kuijper},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2020/11/Biosig_privacy.pdf},

issn = {1617-5468},

year  = {2020},

date = {2020-09-16},

booktitle = {Proceedings of the International Conference of the Biometrics Special Interest Group (BIOSIG) 2020},

pages = {1-5},

publisher = {IEEE},

abstract = {Biometric data includes privacy-sensitive information, such as soft-biometrics. Soft-biometric privacy enhancing technologies aim at limiting the possibility of deducing such information. Previous works proposed several solutions to this problem using several different evaluation processes, metrics, and attack scenarios. The absence of a standardized evaluation protocol makes a meaningful comparison of these solutions difficult. In this work, we propose privacy evaluation protocols (PEPs) for privacy-enhancing technologies (PETs) dealing with soft-biometric privacy. Our framework evaluates PETs in the most critical scenario of an attacker that knows and adapts to the systems privacy-mechanism. Moreover, our PEPs differentiate between PET of learning-based or training-free nature. To ensure that our protocol meets the highest standards in both cases, it is based on Kerckhoffs‘s principle of cryptography.},

keywords = {face recognition, privacy, privacy protection, soft biometric privacy},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {face alignment, face recognition, landmarking},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {face recognition, IoT, PI, proof of concept},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {face, face hallucination, face recognition, performance evaluation, super-resolution},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {biometrics, competition, face recognition, group evaluation, PaSC, performance evaluation},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {4SF, biometrics, face alignment, face recognition, LFW, OpenBR, performance evaluation},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {CNN, deep learning, face recognition, IJB-A, IWBF, performance evaluation, similarity learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {3d face recognition, binary descriptors, face recognition, FREAK, performance comparison, performance evaluation, SIFT},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {biometrics, competition, face recognition, group evaluation, IJCB, PaSC, performance evaluation},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {competition, erk, face recognition, face verification, group evaluation, ICB, mobile biometrics, MOBIO, performance evaluation},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {3d face recognition, biometrics, covariance descriptors, face recognition, face verification, FG, gaussian mixture models, GMM, unscented transform},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {biometrics, competition, face recognition, face verification, group evaluation, mobile biometrics, MOBIO, performance evaluation},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {biometrics, dense SIFT, face recognition, performance evaluation, SIFT, SIFT features},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {biometrics, face recognition, face verification, illumination changes, illumination invariance, nuisance attribute projection, robust recognition},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {biometrics, face recognition, face verification, ICPR, performance evaluation, subspace projection},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {biometrics, erk, face recognition, face verification, performance evaluation, sparse projection analysis},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {biometrics, face recognition, face verification, image degradations, performance evaluation},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {biometrics, face recognition, face verification, histogram remapping, performance evaluation, preprocessing},

pubstate = {published},

tppubtype = {inproceedings}

}