将C1特征应用于静态图像人脸表情识别,提出了一种新的基于生物启发特征和SVM的表情识别算法。提取人脸图像的C1特征,利用PCA+LDA方法对特征进行降维,用SVM进行分类。在JAFFE和Extended Cohn-Kanade(CK+)人脸表情数据库上的实验结果表明,该算法具有较高的识别率,是一种有效的人脸表情识别方法。%C1 features are introduced to facial expression recognition for static images, and a new algorithm for facial expression recognition based on Biologically Inspired Features(BIFs)and SVM is proposed. C1 features of the facial images are extracted, PCA+LDA method is used to reduce the dimensionality of the C1 features, SVM is used for classifi-cation of the expression. The experiments on the JAFFE and Extended Cohn-Kanade(CK+)facial expression data sets show the effectiveness and the good performance of the algorithm.
展开▼