Objave

@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 = {AWE, AWE dataset, biometrics, ear alignment, ear recognition, image alignment, Ransac, SIFT},

pubstate = {published},

tppubtype = {inproceedings}

}

@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}

}

@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{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}

}

@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 = {biometrics, CNN, deep learning, deep models, face verification, similarity learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {biometrics, face verification, Gabor features, image descriptors, LBP, multi modality, PaSC, performance evaluation},

pubstate = {published},

tppubtype = {inproceedings}

}

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

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {DEID, FG, speech deidentification, speech recognition, speech synthesis, speech technologies},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {biometrics, BWild, FG, Gabor features, PaSC, plda, probabilistic Gabor Fisher classifier, probabilistic linear discriminant analysis},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {annotated data, dataset, dataset of emotional speech, EmoLUKS, emotional speech synthesis, speech synthesis, speech technologies, transcriptions},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {3d landmarking, facial landmarking, landmark localization, landmarking, ridge regression, SDM},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {3d face recognition, binary descriptors, biometrics, BRISK, CASIA, face verification, FREAK, FRGC, MCPR, ORB, performance evaluation, SIFT, SURF},

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{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 = {computer vision, deidentification, MIPRO, privacy protection, tattoo deidentification},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {acustic features, biometrics, duration, duration modeling, i-vector, i-vector challenge, Odyssey, performance evaluation, speaker recognition, speech technologies},

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{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 = {3d face recognition, biometrics, covariance descriptor, face verification, FRGC, GMM, modeling, performance evaluation, region-covariance matrix},

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{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 = {biometrics, face verification, FRGC, ICASSP, patch-wise approach, plda, probabilistic linear discriminant analysis},

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{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 = {ASEF, correlation filters, eye localization, face image processing, landmark localization, landmarking, PSEF},

pubstate = {published},

tppubtype = {inproceedings}

}

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

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{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 = {acustic features, canonical correlations, emotion recognition, facial expression recognition, multi modality, speech processing, speech technologies},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {emotion recognition, facial expression recognition, multi modality, speech processing, speech technologies, spontaneous emotions, video processing},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {ASEF, correlation filters, eye localization, face image processing, landmark localization, PSEF},

pubstate = {published},

tppubtype = {inproceedings}

}