Expression recognition from video using a coupled hidden Markov model

To classify the face expressions in the video, in this paper, a system including both facial feature extraction and expression recognition is presented. The facial feature points are tracked first, then a sequence of FAP based face motion vector are deduced. These vectors are divided into two classifications, one for face expression, the other is for visual speech. Finally, a coupled hidden Markov model is trained to perform the recognition. The experimental results show that our approach is better than conventional face expression recognition system.

[1]  L. Rabiner,et al.  An introduction to hidden Markov models , 1986, IEEE ASSP Magazine.

[2]  Takeo Kanade,et al.  Subtly different facial expression recognition and expression intensity estimation , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[3]  Nicu Sebe,et al.  Facial expression recognition from video sequences: temporal and static modeling , 2003, Comput. Vis. Image Underst..

[4]  Kevin P. Murphy,et al.  A coupled HMM for audio-visual speech recognition , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5]  Nicu Sebe,et al.  Facial expression recognition from video sequences , 2002, Proceedings. IEEE International Conference on Multimedia and Expo.

[6]  Kuntal Sengupta,et al.  A hybrid approach of NN and HMM for facial emotion classification , 2002, Pattern Recognit. Lett..

[7]  Christoph Bregler,et al.  Eigen-points [image matching] , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[8]  P. Ekman,et al.  Strong evidence for universals in facial expressions: a reply to Russell's mistaken critique. , 1994, Psychological bulletin.

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

[10]  Timothy F. Cootes,et al.  Active Appearance Models , 1998, ECCV.

[11]  Montse Pardàs,et al.  Emotion recognition based on MPEG-4 Facial Animation Parameters , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.