完整的表情识别系统一般包括人脸表情图像捕获、预处理、人脸检测与定位、

人脸分割与归一化、人脸表情特征提取、人脸表情识别。本文着重研究了人脸表

情特征提取、特征选择及表情分类等关键问题，并提出了一些改进的方法，同时

进行了仿真实验-Complete expression recognition systems typically include facial expression image capture, preprocessing, face detection and location, face segmentation and normalization, facial expression feature extraction, facial expression recognition. Paper focuses on the facial expression feature extraction, feature selection and classification of facial expressions and other key issues and put forward a number of improved methods, and simulation experiment