A Key Frame Selection-Based Facial Expression Recognition System

Automatic recognition of facial expressions has received considerable interest in the computer vision. This paper presents a key frame selection-based system for recognition of four basic facial expressions: happiness, anger, sadness and surprise, in image sequences. The proposed new approach is designed for recognition of facial expressions via a key frame selection of the facial motion from an image sequence where an optical flow is used to determine changes in a facial expression, experimental results demonstrate that the proposed automatic recognition process significantly improves the computational complexity encountered in facial expression recognition while enhancing the ability of recognition

[1]  Siu Cheung Hui,et al.  Facial expression recognition from line-based caricatures , 2003, IEEE Trans. Syst. Man Cybern. Part A.

[2]  Yongsheng Gao,et al.  Face Recognition Using Line Edge Map , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Maja Pantic,et al.  Expert system for automatic analysis of facial expressions , 2000, Image Vis. Comput..

[4]  Ronald Chung,et al.  Facial expression recognition approach for performance animation , 2001, Proceedings Second International Workshop on Digital and Computational Video.

[5]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[6]  Marian Stewart Bartlett,et al.  Classifying Facial Actions , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Hartmut Neven,et al.  Online facial expression recognition based on personalized galleries , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[8]  Anil K. Jain,et al.  Face Detection in Color Images , 2002, IEEE Trans. Pattern Anal. Mach. Intell..