基于SVM信息融合方法的人脸表情识别

Facial Expression Recognition Based on SVM Information Fusion

提出一种基于支持向量机(SVM)的信息融合方法进行人脸表情识别．该方法首先对 预处理后的人脸图像进行局部特征和整体特征的提取;然后用最小距离分类器、最近邻距离 分类器、最大相关分类器、径向基函数(RBF)神经网络分类器进行表情识别;最后构造一 个三阶的多项式支持向量机对多个分类器的输出进行决策融合以达到人脸表情识别的目的．

In this paper, an algorithm for facial expression recognition based on information fusion in SVM with multi-features and multi-classifiers is proposed. First, some local features and global features from pre-processed face images are obtained. Then four classifiers are used to classify those features. Finally, the outputs of four classifiers are input to SVM information fusion to get facial expression recognition. The proposed algorithm with images from the Yale face database and JAFFEE database is tested and the results show the algorithm is effective.