A face sequence recognition method based on deep convolutional neural network

Although the research in the field of face recognition has achieved high-quality results in the controllable production environment, its further research is limited in the field of face facial expression recognition based on video streaming. This paper describes the recent experimental research progress of a project, an analysis system of students' attendance status designed for real-time face recognition and prediction in class. In this paper, an expression recognition model based on mini-Xcetion optimization is proposed and the experimental results show that the facial expression recognition accuracy of this model is up to 98.96%, which is better than other algorithms in accuracy and more suitable for the application requirements of the system under the target scene studied.