Teacher-directed learning in view-independent face recognition with mixture of experts using single-view eigenspaces

Abstract We propose a new model for view-independent face recognition by multiview approach. We use the so-called “mixture of experts”, ME, in which, the problem space is divided into several subspaces for the experts, and the outputs of experts are combined by a gating network. In our model, instead of leaving the ME to partition the face space automatically, the ME is directed to adapt to a particular partitioning corresponding to predetermined views. To force an expert towards a specific view of face, in the representation layer, we provide each expert with its own eigenspace computed from the faces in the corresponding view. Furthermore, we use teacher-directed learning, TDL, in a way that according to the pose of the input training sample, only the weights of the corresponding expert are updated. The experimental results support our claim that directing the experts to a predetermined partitioning of face space improves the performance of the conventional ME for view-independent face recognition. In particular, for 1200 images of unseen intermediate views of faces from 20 subjects, the ME with single-view eigenspaces yields the average recognition rate of 80.51% in 10 trials, which is noticeably increased to 90.29% by applying the TDL method.

[1]  Elif Derya Übeyli,et al.  Determining variability of ophthalmic arterial Doppler signals using Lyapunov exponents , 2004, Comput. Biol. Medicine.

[2]  James C. Bezdek,et al.  Decision templates for multiple classifier fusion: an experimental comparison , 2001, Pattern Recognit..

[3]  Josef Kittler,et al.  Design and Fusion of Pose-Invariant Face-Identification Experts , 2006, IEEE Transactions on Circuits and Systems for Video Technology.

[4]  Ryotaro Kamimura,et al.  Teacher-Directed Learning with Gaussian and Sigmoid Activation Functions , 2004, ICONIP.

[5]  Ronald L. Rivest,et al.  Learning binary relations, total orders, and read-once formulas , 1990 .

[6]  Alex Pentland,et al.  Probabilistic Visual Learning for Object Representation , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Luc Vandendorpe,et al.  Combining face verification experts , 2002, Object recognition supported by user interaction for service robots.

[8]  Zhi-Hua Zhou,et al.  Face recognition from a single image per person: A survey , 2006, Pattern Recognit..

[9]  Reza Ebrahimpour,et al.  Teacher-Directed Learning with Mixture of Experts for View-Independent Face Recognition , 2007, SOFSEM.

[10]  Hiroshi Murase,et al.  Visual learning and recognition of 3-d objects from appearance , 2005, International Journal of Computer Vision.

[11]  Shimon Ullman,et al.  Recognition invariance obtained by extended and invariant features , 2004, Neural Networks.

[12]  David Beymer,et al.  Face recognition under varying pose , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Balas K. Natarajan,et al.  On learning Boolean functions , 1987, STOC.

[14]  Simon Kasif,et al.  Learning with a Helpful Teacher , 1991, IJCAI.

[15]  Rabab Kreidieh Ward,et al.  Face recognition under pose variations , 2006, J. Frankl. Inst..

[16]  Terence Sim,et al.  The CMU Pose, Illumination, and Expression Database , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Andrew Tomkins,et al.  A computational model of teaching , 1992, COLT '92.

[18]  M. Kearns,et al.  On the complexity of teaching , 1991, COLT '91.

[19]  Ke Chen,et al.  Improved learning algorithms for mixture of experts in multiclass classification , 1999, Neural Networks.

[20]  Reza Ebrahimpour,et al.  Face Detection Using Mixture of MLP Experts , 2007, Neural Processing Letters.

[21]  A. S. Tolba,et al.  Combined Classifiers for Invariant Face Recognition , 1999, Proceedings 1999 International Conference on Information Intelligence and Systems (Cat. No.PR00446).

[22]  Xia Hong,et al.  A Mixture of Experts Network Structure Construction Algorithm for Modelling and Control , 2001, Applied Intelligence.

[23]  Norbert Krüger,et al.  Face Recognition by Elastic Bunch Graph Matching , 1997, CAIP.

[24]  Timothy F. Cootes,et al.  Active Appearance Models , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[26]  Azriel Rosenfeld,et al.  Face recognition: A literature survey , 2003, CSUR.

[27]  Lawrence Sirovich,et al.  Application of the Karhunen-Loeve Procedure for the Characterization of Human Faces , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[29]  Garrison W. Cottrell,et al.  Organization of face and object recognition in modular neural network models , 1999, Neural Networks.

[30]  Subhash C. Bagui,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2005, Technometrics.

[31]  Alex Pentland,et al.  View-based and modular eigenspaces for face recognition , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[32]  Reza Ghaderi.  Arranging simple neural networks to solve complex classification problems , 2000 .

[33]  John A. Mills,et al.  A mixture of experts committee machine to design compensators for intensity modulated radiation therapy , 2006, Pattern Recognit..

[34]  H. David Mathias,et al.  DNF—if you can't learn'em, teach'em: an interactive model of teaching , 1995, COLT '95.

[35]  Sally A. Goldman,et al.  Teaching a smart learner , 1993, COLT '93.

[36]  Elif Derya Übeyli,et al.  A modified mixture of experts network structure for ECG beats classification with diverse features , 2005, Eng. Appl. Artif. Intell..

[37]  Abdenour Hadid,et al.  Face recognition under varying views , 2000, Computers and Their Applications.

[38]  Barbara Zitov a.  Journal of the Franklin Institute , 1942, Nature.

[39]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[40]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[41]  Ayumi Shinohara,et al.  Teachability in computational learning , 1990, New Generation Computing.

[42]  Patrick J. Flynn,et al.  A survey of approaches and challenges in 3D and multi-modal 3D + 2D face recognition , 2006, Comput. Vis. Image Underst..

[43]  Sally A. Goldman,et al.  Teaching a Smarter Learner , 1996, J. Comput. Syst. Sci..

[44]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[45]  Konstantinos N. Plataniotis,et al.  Face recognition using kernel direct discriminant analysis algorithms , 2003, IEEE Trans. Neural Networks.

[46]  Josef Kittler,et al.  Combining Classifier for Face Identification at Unknown Views with a Single Model Image , 2004, SSPR/SPR.

[47]  Anil K. Jain,et al.  Integrating Faces and Fingerprints for Personal Identification , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[48]  Norbert Krüger,et al.  Face Recognition by Elastic Bunch Graph Matching , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[49]  L Sirovich,et al.  Low-dimensional procedure for the characterization of human faces. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[50]  Michael R. Lyu,et al.  Face recognition committee machine , 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).

[51]  Ronald L. Rivest,et al.  Learning Binary Relations and Total Orders , 1989, COLT 1989.

[52]  Luc Vandendorpe,et al.  Enhancing the performance of personal identity authentication systems by fusion of face verification experts , 2002, Proceedings. IEEE International Conference on Multimedia and Expo.

[53]  Ronald L. Rivest,et al.  Being taught can be faster than asking questions , 1995, COLT '95.

[54]  Elif Derya Übeyli,et al.  Improving medical diagnostic accuracy of ultrasound Doppler signals by combining neural network models , 2005, Comput. Biol. Medicine.

[55]  Adam Krzyżak,et al.  Methods of combining multiple classifiers and their applications to handwriting recognition , 1992, IEEE Trans. Syst. Man Cybern..

[56]  Wen Gao,et al.  Information fusion in face identification , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..