Publications

@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}

}

@inproceedings{BTAS2009,

title = {Principal Gabor Filters for Face Recognition},

author = {Vitomir Štruc and Rok Gajšek and Nikola Pavešić},

url = {https://lmi.fe.uni-lj.si/en/principalgaborfiltersforfacerecognition/},

doi = {10.1109/BTAS.2009.5339020},

year  = {2009},

date = {2009-09-01},

urldate = {2009-09-01},

booktitle = {Proceedings of the 3rd IEEE International Conference on Biometrics: Theory, Systems and Applications (BTAS'09)},

pages = {1-6},

publisher = {IEEE},

address = {Washington D.C., U.S.A.},

abstract = {Gabor filters have proven themselves to be a powerful tool for facial feature extraction. An abundance of recognition techniques presented in the literature exploits these filters to achieve robust face recognition. However, while exhibiting desirable properties, such as orientational selectivity or spatial locality, Gabor filters have also some shortcomings which crucially affect the characteristics and size of the Gabor representation of a given face pattern. Amongst these shortcomings the fact that the filters are not orthogonal one to another and are, hence, correlated is probably the most important. This makes the information contained in the Gabor face representation redundant and also affects the size of the representation. To overcome this problem we propose in this paper to employ orthonormal linear combinations of the original Gabor filters rather than the filters themselves for deriving the Gabor face representation. The filters, named principal Gabor filters for the fact that they are computed by means of principal component analysis, are assessed in face recognition experiments performed on the XM2VTS and YaleB databases, where encouraging results are achieved.},

keywords = {biometrics, face verification, feature extraction, Gabor features, performance evaluation, principal Gabor filters},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{InterSp2009,

title = {Emotion recognition using linear transformations in combination with video},

author = {Rok Gajšek and Vitomir Štruc and Simon Dobrišek and France Mihelič},

url = {https://lmi.fe.uni-lj.si/en/emotionrecognitionusinglineartransformationsincombinationwithvideo/},

year  = {2009},

date = {2009-09-01},

urldate = {2009-09-01},

booktitle = {Speech and intelligence: proceedings of Interspeech 2009},

pages = {1967-1970},

address = {Brighton, UK},

abstract = {The paper discuses the usage of linear transformations of Hidden Markov Models, normally employed for speaker and environment adaptation, as a way of extracting the emotional components from the speech. A constrained version of Maximum Likelihood Linear Regression (CMLLR) transformation is used as a feature for classification of normal or aroused emotional state. We present a procedure of incrementally building a set of speaker independent acoustic models, that are used to estimate the CMLLR transformations for emotion classification. An audio-video database of spontaneous emotions (AvID) is briefly presented since it forms the basis for the evaluation of the proposed method. Emotion classification using the video part of the database is also described and the added value of combining the visual information with the audio features is shown.},

keywords = {emotion recognition, facial expression recognition, interspeech, speech, speech technologies, spontaneous emotions},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ERK2009N,

title = {Nuisance Attribute Projection in the Logarithm Domain for Face Recognition under Severe Illumination Changes},

author = {Vitomir Štruc and Zongmin Ma and Nikola Pavešić},

year  = {2009},

date = {2009-09-01},

booktitle = {Proceedings of the IEEE International Electrotechnical and Computer Science Conference (ERK'09)},

pages = {279-281},

address = {Portorož, Slovenia},

keywords = {biometrics, face verification, illumination changes, illumination invariance, nuisance attribute projection, performance evaluation, robust recognition},

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{Mathmod09,

title = {A comparison of feature normalization techniques for PCA-based palmprint recognition},

author = {Vitomir Štruc and Nikola Pavešić},

url = {https://lmi.fe.uni-lj.si/en/acomparisonoffeaturenormalizationtechniquesforpca-basedpalmprintrecognition/},

year  = {2009},

date = {2009-02-01},

urldate = {2009-02-01},

booktitle = {Proceedings of the International Conference on Mathematical Modeling (MATHMOD'09)},

pages = {2450-2453},

address = {Viena, Austria},

abstract = {Computing user templates (or models) for biometric authentication systems is one of the most crucial steps towards efficient and accurate biometric recognition. The constructed templates should encode user specific information extracted from a sample of a given biometric modality, such as, for example, palmprints, and exhibit a sufficient level of dissimilarity with other templates stored in the systems database. Clearly, the characteristics of the user templates depend on the approach employed for the extraction of biometric features, as well as on the procedure used to normalize the extracted feature vectors. While feature-extraction methods are a well studied topic, for which a vast amount of comparative studies can be found in the literature, normalization techniques lack such studies and are only briefly mentioned in most cases. In this paper we, therefore, apply several normalization techniques to feature vectors extracted from palmprint images by means of principal component analysis (PCA) and perform a comparative analysis on the results. We show that the choice of an appropriate normalization technique greatly influences the performance of the palmprint-based authentication system and can result in error rate reductions of more than 30%.},

keywords = {biometrics, face verification, feature normalization, normalization, pca, 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}

}