Facial expression recognition based on feature selection by quadratic mutual information.
- Author:
Ling ZHANG
1
;
Yuanwen ZOU
;
Tianfu WANG
;
Jiangli LIN
;
Deyu LI
Author Information
1. Department of Biomedical Engineering of Sichuan University, Chengdu 610065, China.
- Publication Type:Journal Article
- MeSH:
Algorithms;
Computer Simulation;
Facial Expression;
Humans;
Image Interpretation, Computer-Assisted;
methods;
Models, Biological;
Pattern Recognition, Automated;
methods;
Signal Processing, Computer-Assisted
- From:
Journal of Biomedical Engineering
2008;25(3):510-514
- CountryChina
- Language:Chinese
-
Abstract:
To solve the problem of imprecise positioning of feature point and of the feature data redundancy in facial expression recognition by active appearance models (AAM), the automatic adjustment of initial model for AAM fitting is proposed in this paper. The specific aims are to improve the precision of positioning and to more effectively reflect the variation of expressions by acquired features. The problem of feature selection is resolved by adopting quadratic mutual information and reducing the feature dimension. The support vector machine (SVM) classifier is used for expression recognition. The experimental results on CAS-PEAL facial expression database show that the proposed method effectively improves the performance of facial expression recognition, the maximum recognition rate being 83.33%.
