Research and design of face and expression recognition system based on convolutional neural network

With the development of human-computer interaction technology and machine learning technology, facial expression recognition technology has gradually become a research hotspot. In recent years, with the rapid development of convolutional neural network and facial expression recognition, automatic facial expression recognition system has been widely used. In this paper, the method of facial expression recognition based on convolution neural network is studied. Because the differences between facial expressions are very subtle, in order to improve the ability of convolution neural network to extract facial expression features and its recognition accuracy, continuous convolution is introduced into convolution neural network model. The improved model uses small-scale convolution kernel to make the extracted facial expression features more precise, Two continuous convolution layers enhance the nonlinear expression ability of the model. With the development of human-computer interaction technology and machine learning technology, facial expression recognition technology has gradually become a research hotspot.