A Review of Facial Expression Recognition

Abstract

With the development of deep learning, deep learning is becoming more and more common for facial recognition. We summarize some widely used public data sets for facial expression recognition; The basic flow of facial expression recognition is briefly introduced. This paper mainly analyzes some existing deep learning methods, especially deep convolutional neural network. The structure analysis and performance comparison of four classical convolutional neural networks (AlexNet, GoogleNet, VGGNet and ResNet) are carried out. Finally, the present research on expression recognition is summarized and prospected.