Facial expression recognition method and system based on cross fusion of local and global information

The invention discloses a local and global information cross fusion facial expression recognition method and system. The method comprises the following steps: S1, acquiring a face image data set; s2, obtaining a facial expression recognition model according to the facial image data set; and S3, inputting a to-be-processed face image into the face expression recognition model, and performing real-time expression recognition. According to the technical scheme, more accurate expression recognition performance can be obtained. 本发明公开一种局部全局信息交叉融合的面部表情识别方法和系统，包括以下步骤：步骤S1、获取人脸图像数据集；步骤S2、根据人脸图像数据集，得到人脸表情识别模型；步骤S3、将待处理的人脸图像输入到人脸表情识别模型中，进行实时表情识别。本发明的技术方案，可以得到更精确的表情识别性能。