Design of a Fast Recognition Method for College Students’ Classroom Expression Images Based on Deep Learning

The expressions of students in class will directly reflect their classroom state. Therefore, this paper proposes a fast recognition method for college students’ classroom expression images based on deep learning. Firstly, the college students’ classroom expression images are processed by histogram equalization, graying and clipping to avoid other factors affecting the recognition results of expression images. Secondly, the convolution neural network in deep learning method is used to extract the features of college students’ classroom expression images. Finally, support vector machine is used to complete the rapid recognition of college students’ classroom expression images. The experimental results show that, compared with the traditional facial expression image recognition methods, this method can improve the recognition accuracy of facial expression images, and shorten the recognition time with an average of 15.1 s.