A New Classifier for Facial Expression Recognition: Fuzzy Buried Markov Model

To overcome the disadvantage of classical recognition model that cannot perform well enough when there are some noises or lost frames in expression image sequences, a novel model called fuzzy buried Markov model (FBMM) is presented in this paper. FBMM relaxes conditional independence assumptions for classical hidden Markov model (HMM) by adding the specific cross-observation dependencies between observation elements. Compared with buried Markov model (BMM), FBMM utilizes cloud distribution to replace probability distribution to describe state transition and observation symbol generation and adopts maximum mutual information (MMI) method to replace maximum likelihood (ML) method to estimate parameters. Theoretical justifications and experimental results verify higher recognition rate and stronger robustness of facial expression recognition for image sequences based on FBMM than those of HMM and BMM.

[1]  Aggelos K. Katsaggelos,et al.  Automatic facial expression recognition using facial animation parameters and multistream HMMs , 2006, IEEE Transactions on Information Forensics and Security.

[2]  Zhou Xiao.  Real-time Facial Expression Recognition Based on Boosted Embedded Hidden Markov Model , 2005 .

[3]  Fan Zhou,et al.  Connectivity Compression for Stripified Triangle Meshes Using Basic Strips , 2007, Fourth International Conference on Image and Graphics (ICIG 2007).

[4]  Mehmet Celenk,et al.  Spatio-temporal modeling of facial expressions using Gabor-wavelets and hierarchical hidden Markov models , 2005, IEEE International Conference on Image Processing 2005.

[5]  C.S. Lima,et al.  Cardiac Arrhythmia Detection by Parameters Sharing and MMIE Training of Hidden Markov Models , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[6]  Donghyun Kim,et al.  Linear Spectral Transformation for Robust Speech Recognition Using Maximum Mutual Information , 2007, IEEE Signal Processing Letters.

[7]  Du-Ming Tsai,et al.  Defect detection in periodically patterned surfaces using independent component analysis , 2008, Pattern Recognit..

[8]  Naohito Okude,et al.  Bayesian networks layer model to represent anesthetic practice , 2007, 2007 IEEE International Conference on Systems, Man and Cybernetics.

[9]  Kun Yu,et al.  Local Gabor Fisher Classifier for Face Recognition , 2007, Fourth International Conference on Image and Graphics (ICIG 2007).

[10]  Montse Pardàs,et al.  Facial animation parameters extraction and expression recognition using Hidden Markov Models , 2002, Signal Process. Image Commun..

[11]  Honggang Zhang,et al.  Robust Discriminant Analysis of Gabor Feature for Face Recognition , 2007, Fourth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2007).

[12]  C.H. Dai,et al.  Adaptive Probabilities of Crossover and Mutation in Genetic Algorithms Based on Cloud Model , 2006, 2006 IEEE Information Theory Workshop - ITW '06 Chengdu.

[13]  Bo Chen,et al.  A Clustering Based Bayesian Network Classifier , 2007, Fourth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2007).

[14]  Yongzhao Zhan,et al.  Facial Expression Recognition Based on Gabor Wavelet Transformation and Elastic Templates Matching , 2006, Int. J. Image Graph..

[15]  Renato De Mori,et al.  High performance connected digit recognition using maximum mutual information estimation , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[16]  Jeff A. Bilmes,et al.  Buried Markov models: a graphical-modeling approach to automatic speech recognition , 2003, Comput. Speech Lang..

[17]  Qiuqi Ruan,et al.  Two-Dimension PCA for Facial Expression Recognition , 2006, 2006 8th international Conference on Signal Processing.

[18]  Jeff A. Bilmes,et al.  Buried Markov models for speech recognition , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[19]  M. Taheri,et al.  A new method for fuzzy hidden Markov models in speech recognition , 2005, Proceedings of the IEEE Symposium on Emerging Technologies, 2005..