Facial expression recognition based on PCA reconstruction

A facial expression recognition algorithm named PCA (Principal Component Analysis) reconstruction to the still image containing facial expression information is proposed. The general idea of the algorithm is classifying the training sets of facial expression into different subsets by facial expression. Then apply the PCA algorithm into the subsets to get the corresponding orthogonal basis. Test images project on the orthogonal basis of different expression subsets, and reconstruct based on the projection coordinates. Then compare the tested image with the reconstructed images and choose the expression of the most similar one to be the expression of the tested image. The algorithm is tested on Japanese female facial expression (JAFFE) database. The feasibility of the method has been verified by experiment.

[1]  Rong Wang,et al.  The e-Learning System Model Based on Affective Computing , 2008, 2008 Seventh International Conference on Web-based Learning.

[2]  S.C. Tai,et al.  Automatic facial expression recognition system using Neural Networks , 2007, TENCON 2007 - 2007 IEEE Region 10 Conference.

[3]  Gwen Littlewort,et al.  Dynamics of Facial Expression Extracted Automatically from Video , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[4]  Narendra Ahuja,et al.  Facial expression decomposition , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[5]  Zhiliang Wang,et al.  Real-Time Facial Expression Recognition System Based on HMM and Feature Point Localization , 2005, ACII.

[6]  Takeo Kanade,et al.  Comprehensive database for facial expression analysis , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[7]  Maja Pantic,et al.  Facial action recognition for facial expression analysis from static face images , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[8]  Lisa M. Brown,et al.  Real World Real-time Automatic Recognition of Facial Expressions , 2003 .