Image recognition based on separable lattice trajectory 2-D HMMS

In this paper, a novel statistical model for image recognition based on separable lattice 2-D HMMs (SL2D-HMMs) is proposed. Although SL2D-HMMs can model invariance to size and location deformation, its modeling accuracy is still insufficient because of the following two assumptions: i) the statistics of each state are constant and ii) the state output probabilities are conditionally independent. In this paper, SL2D-HMMs are reformulated as a trajectory model that can capture dependencies between adjacent observations. The effectiveness of the proposed model was demonstrated in face recognition and image alignment experiments.

[1]  Yoshihiko Nankaku,et al.  Face recognition based on extended separable lattice 2-D HMMS , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[2]  Heiga Zen,et al.  Product of Experts for Statistical Parametric Speech Synthesis , 2012, IEEE Transactions on Audio, Speech, and Language Processing.

[3]  Nankaku Yoshihiko,et al.  Face recognition based on extended separable lattice HMMs , 2010 .

[4]  Yoshihiko Nankaku,et al.  An extension of Separable Lattice 2-D HMMS for rotational data variations , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[5]  Chih-Pin Liao,et al.  Maximum Confidence Hidden Markov Modeling for Face Recognition , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Max Welling,et al.  Product of experts , 2007, Scholarpedia.

[7]  Yoshihiko Nankaku,et al.  Face Recognition using Hidden Markov Eigenface Models , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[8]  Yoshihiko Nankaku,et al.  Face Recognition Based on Separable Lattice HMMS , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[9]  Leonhard Held,et al.  Gaussian Markov Random Fields: Theory and Applications , 2005 .

[10]  Seiichi Nakagawa,et al.  A Survey on Automatic Speech Recognition , 2002 .

[11]  Hisham Othman,et al.  A simplified second-order HMM with application to face recognition , 2001, ISCAS 2001. The 2001 IEEE International Symposium on Circuits and Systems (Cat. No.01CH37196).

[12]  Monson H. Hayes,et al.  Maximum likelihood training of the embedded HMM for face detection and recognition , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[13]  Seiichi Uchida,et al.  An Approximation Algorithm for Two-Dimensional Warping , 2000 .

[14]  Seiichi Uchida,et al.  Piecewise linear two-dimensional warping , 1999, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[15]  Robert M. Gray,et al.  Image classification by a two dimensional hidden Markov model , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[16]  Michael I. Jordan,et al.  Factorial Hidden Markov Models , 1995, Machine Learning.

[17]  K. Tokuda,et al.  Speech parameter generation from HMM using dynamic features , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[18]  Oscar E. Agazzi,et al.  Keyword Spotting in Poorly Printed Documents using Pseudo 2-D Hidden Markov Models , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[20]  Roberto Pieraccini,et al.  Dynamic planar warping for optical character recognition , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[21]  Alex Pentland,et al.  Face recognition using eigenfaces , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

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

[23]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[24]  Sadaoki Furui,et al.  Speaker-independent isolated word recognition using dynamic features of speech spectrum , 1986, IEEE Trans. Acoust. Speech Signal Process..

[25]  Andrew J. Viterbi,et al.  Error bounds for convolutional codes and an asymptotically optimum decoding algorithm , 1967, IEEE Trans. Inf. Theory.

[26]  Yuichi Yaguchi,et al.  Full Pixel Matching between Images for Non-linear Registration of Objects , 2010, IPSJ Trans. Comput. Vis. Appl..

[27]  Heiga Zen,et al.  Reformulating the HMM as a trajectory model by imposing explicit relationships between static and dynamic feature vector sequences , 2007, Comput. Speech Lang..

[28]  Mark J. F. Gales,et al.  Product of Gaussians for speech recognition , 2006, Comput. Speech Lang..

[29]  Dustin Boswell,et al.  Introduction to Support Vector Machines , 2002 .

[30]  Jiri Matas,et al.  XM2VTSDB: The Extended M2VTS Database , 1999 .

[31]  Shaogang Gong,et al.  Audio- and Video-based Biometric Person Authentication , 1997, Lecture Notes in Computer Science.

[32]  Douglas A. Reynolds,et al.  Robust text-independent speaker identification using Gaussian mixture speaker models , 1995, IEEE Trans. Speech Audio Process..

[33]  Shigeaki Watanabe,et al.  Subspace method to pattern recognition , 1973 .