Abstract: The paper discusses facial expression recognition based on image algebraic characters. First, eyes and mouth are segmented from the facial expression image and variant moments and singular value feature vectors of eyes and mouth are extracted. Then Fisher linear discriminant analysis is used to find a set of optimal feature vectors. Finally, It trains a SVM classifier. The results show that the presented method has a higher accuracy and robust performance

Key words: Invariant moments; Singular value decomposition (SVD); Fisher linear discriminate analysis; Support vector machine (SVM); Facial expression recognition

摘要： 探讨了图像代数特征在面部表情识别中的应用，首先对面部表情图像进行了分割，得到眼睛和嘴巴区域，然后分别对眼睛和嘴巴区域提取不变矩和奇异值特征向量，并进行Fisher 线性判别分析，最后训练了支持向量机分类器。实验结果表明该方法取得了比较好的识别效果。

关键词: 不变矩；奇异值分解；Fisher 线性判别分析；支持向量机；面部表情识别