221 results found
Zafeiriou S, Tzimiropoulos G, Pantic M, 2011, Subspace analysis of arbitrarily many linear filter responses with an application to face tracking, Pages: 37-42, ISSN: 2160-7508
Multi-scale/orientation local image analysis methods are valuable tools for obtaining highly distinctive image-based representations. Very often, these features are generated from the responses of a bank of linear filters corresponding to different scales and orientations. Naturally, as the number of filters increases, so does the feature dimensionality. Further processing is often feasible only when dimensionality reduction is performed by subspace learning techniques, such as Principal Component analysis (PCA) or Linear Discriminant Analysis (LDA). The major problem stems from the fact that as the number of features increases, so does the computational complexity of these methods which, in turn, limits the number of scales and orientations examined. In this paper, we show how linear subspace analysis on features generated by the response of linear filter banks can be efficiently re-formulated such that complexity does not depend on the number of filters used. We describe computationally efficient and exact versions of PCA while the extension to other subspace learning algorithms is straightforward. Finally, we show how the proposed methods can boost the performance of algorithms for appearance based tracking algorithm. © 2011 IEEE.
Zafeiriou S, Pantic M, 2011, Facial behaviometrics: The case of facial deformation in spontaneous smile/laughter, Pages: 13-19, ISSN: 2160-7508
In this paper we explore the use of dense facial deformation in spontaneous smile/laughter as a biometric signature. The facial deformation is calculated between a neutral image (as neutral we define the least expressive image of the smile/laughter episode) and the apex of spontaneous smile/laughter (as apex we define the frame of the maximum facial change/deformation) and its complex representation is regarded. Subsequently, supervised and unsupervised complex dimensionality reduction techniques, namely the complex Principal Component Analysis (PCA) and the complex Linear Discriminant Analysis (LDA), are applied at the complex vector fields for feature extraction. We demonstrate the efficacy of facial deformation as a mean for person verification in a database of spontaneous smiles/laughters. © 2011 IEEE.
Tzimiropoulos G, Zafeiriou S, Pantic M, 2011, Robust and efficient parametric face alignment, ICCV 2011, Publisher: IEEE, Pages: 1847-1854, ISSN: 1550-5499
Zafeiriou S, Petrou M, 2010, Sparse representations for facial expressions recognition via l<inf>1</inf> optimization, Pages: 32-39
In this paper, the principles of sparse signal representation theory are explored in order to perform facial expressions recognition from frontal views. Motivated by the success such methods have demonstrated in the face recognition problem, we formulate the feature extraction procedure in order to achieve facial expression recognition as an l1 optimization problem. We show that the straightforward application of these methods to expressive images imposes certain difficulties. The use of difference images (i.e., the images that are derived from the subtraction of the neutral image from the expressive one) for sparse facial expression representations is justified. The use of expressive facial grids for similar tasks is also studied. Finally, the robustness of the proposed representations under facial image occlusion is shown and the efficacy of the proposed method in a series of experiments is demonstrated © 2010 IEEE.
Zafeiriou S, Laskaris N, 2010, Nonnegative Embeddings and Projections for Dimensionality Reduction and Information Visualization, 2010 20th International Conference on Pattern Recognition (ICPR), Publisher: IEEE
Argyriou V, Sevaslidou M, Zafeiriou S, 2010, Virtual university as a role playing game, Pages: 743-747
Research and development in design of games for education focus on understanding better what features of games can be inherited to further motivate students and simultaneously improve learning outcomes. Since, a common design standard is not available for educational games solutions are usually carried out by an ad hoc process. In this paper, a novel approach to design this kind of games is presented taking into consideration key features of the most successful massively multiplayer online role-playing games (MMORPG). The proposed design incorporates fun and learning through the key ingredients of MMORPGs that make them 'addictive' keeping the players constantly motivated. Our main contribution is to suggest design issues that should be taken into consideration when designing educational games. © 2010 IEEE.
Tzimiropoulos G, Argyriou V, Zafeiriou S, et al., 2010, Robust FFT-Based Scale-Invariant Image Registration with Image Gradients, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol: 32, Pages: 1899-1906, ISSN: 0162-8828
Nikolopoulos S, Zafeiriou S, Nikolaidis N, et al., 2010, Image replica detection system utilizing R-trees and linear discriminant analysis, Pattern Recognition, Vol: 43, Pages: 636-649, ISSN: 0031-3203
Toderici G, Passalis G, Zafeiriou S, et al., 2010, Bidirectional relighting for 3D-aided 2D Face Recognition, 23rd IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Publisher: IEEE COMPUTER SOC, Pages: 2721-2728, ISSN: 1063-6919
Zafeiriou S, Hansen MF, Atkinson GA, et al., 2010, Baseline face recognition using photometric stereo data, International Conference and Exhibition on Biometrics Technology, Publisher: ELSEVIER SCIENCE BV, Pages: 20-25, ISSN: 1877-0509
Zafeiriou S, Petrou M, 2010, Nonlinear non-negative component analysis algorithms, Image Processing, IEEE Transactions on, Vol: 19, Pages: 1050-1066
Tzimiropoulos G, Zafeiriou S, 2010, On the Subspace of Image Gradient Orientations, CoRR, Vol: abs/1005.2715
Zafeiriou S, Petrou M, Argyriou V, 2009, 2.5D elastic graph matching algorithms, Pages: 703-710
In this paper, a series of advances in Elastic Graph Matching (EGM) for face recognition assisted by the availability of 3D facial geometry is proposed. More specifically, we conceptually extend the EGM algorithm in order to exploit the 3D nature of human facial geometry for face recognition/verification. In order to achieve that, first we extend the matching module of the EGM algorithm in order to capitalize on the 2.5D facial data. Moreover, we incorporate the 3D geometry into the multiscale analysis used and build a novel geodesic multiscale morphological pyramid of dilations/erosions in order to fill the graph jets. We demonstrate the effficiency of the proposed advances in the face recognition/verification problem. ©2009 IEEE.
Laskaris NA, Zafeiriou SP, Garefa L, 2009, Use of random time-intervals (RTIs) generation for biometric verification, Pattern Recognition, Vol: 42, Pages: 2787-2796, ISSN: 0031-3203
Zafeiriou S, 2009, Discriminant Nonnegative Tensor Factorization Algorithms, IEEE TRANSACTIONS ON NEURAL NETWORKS, Vol: 20, Pages: 217-235, ISSN: 1045-9227
Kotsia I, Zafeiriou S, Pitas I, 2009, Novel Multiclass Classifiers Based on the Minimization of the Within-Class Variance, IEEE TRANSACTIONS ON NEURAL NETWORKS, Vol: 20, Pages: 14-34, ISSN: 1045-9227
Zafeiriou S, Petrou M, 2009, Nonlinear nonnegative component analysis, Pages: 2860-2865
In this paper general solutions for Nonlinear Nonnega- tive Component Analysis for data representation and recog- nition are proposed. That is, motivated by a combination of the Nonnegative Matrix Factorization (NMF) algorithm and kernel theory, which has lead to an NMF algorithm in a polynomial feature space , we propose a general frame- work where one can build a nonlinear nonnegative compo- nent analysis using kernels, the so-called Projected Gradi- ent Kernel Nonnegative Matrix Factorization (PGKNMF). In the proposed approach, arbitrary positive kernels can be adopted while at the same time it is ensured that the limit point of the procedure is a stationary point of the optimiza- tion problem. Moreover, we propose fixed point algorithms for the special case of Radial Basis Function (RBF) kernels. We demonstrate the power of the proposed methods in face and facial expression recognition applications. © 2009 IEEE.
Zafeiriou S, Petrou M, 2009, Nonlinear Nonnegative Component Analysis, IEEE-Computer-Society Conference on Computer Vision and Pattern Recognition Workshops, Publisher: IEEE, Pages: 2852-2857, ISSN: 1063-6919
Zafeiriou S, Pitas I, 2008, Discriminant Graph Structures for Facial Expression Recognition, IEEE TRANSACTIONS ON MULTIMEDIA, Vol: 10, Pages: 1528-1540, ISSN: 1520-9210
Nikitidis S, Zafeiriou S, Pitas I, 2008, Camera Motion Estimation Using a Novel Online Vector Field Model in Particle Filters, IEEE Transactions on Circuits and Systems for Video Technology, Vol: 18, Pages: 1028-1039, ISSN: 1051-8215
Laskaris NA, Zafeiriou SP, 2008, Beyond FCM: Graph-theoretic post-processing algorithms for learning and representing the data structure, Pattern Recognition, Vol: 41, Pages: 2630-2644, ISSN: 0031-3203
Kotsia I, Zafeiriou S, Pitas I, 2008, Texture and shape information fusion for facial expression and facial action unit recognition, Pattern Recognition, Vol: 41, Pages: 833-851, ISSN: 0031-3203
Kotsia I, Zafeiriou S, Nikolaidis N, et al., 2008, Texture and Shape Information Fusion for Facial Action Unit Recognition, First International Conference on Advances in Computer-Human Interaction, Publisher: IEEE
Goudelis G, Zafeiriou S, Tefas A, et al., 2008, Motivating class-specific nonlinear projections for single and multiple view face verification., Publisher: IEEE, Pages: 2752-2755
Nikitidis S, Zafeiriou S, Pitas I, 2008, Camera Motion Estimation Using Particle Filters., Publisher: INSTICC - Institute for Systems and Technologies of Information, Control and Communication, Pages: 670-673
Kotsia I, Zafeiriou S, Pitas I, 2008, Discriminant Non-negative Matrix Factorization and Projected Gradients for Frontal Face Verification., Publisher: Springer, Pages: 82-90
Zafeiriou S, Tefas A, Pitas I, 2007, Minimum Class Variance Support Vector Machines, IEEE Transactions on Image Processing, Vol: 16, Pages: 2551-2564, ISSN: 1057-7149
Zafeiriou S, Tefas A, Pitas I, 2007, The discriminant elastic graph matching algorithm applied to frontal face verification, Pattern Recognition, Vol: 40, Pages: 2798-2810, ISSN: 0031-3203
Goudelis G, Zafeiriou S, Tefas A, et al., 2007, Class-Specific Kernel-Discriminant Analysis for Face Verification, IEEE Transactions on Information Forensics and Security, Vol: 2, Pages: 570-587, ISSN: 1556-6013
Kotsia I, Zafeiriou S, Pitas I, 2007, A Novel Discriminant Non-Negative Matrix Factorization Algorithm With Applications to Facial Image Characterization Problems, IEEE Transactions on Information Forensics and Security, Vol: 2, Pages: 588-595, ISSN: 1556-6013
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.