Human Face Expression Recognition Based on Deep Learning-Deep Convolutional Neural Network

In recent years, with the rapid and effective development of deep learning(DL) and deep convolution neural network(DCNN), the traditional facial expression recognition(FER) technology is difficult to meet the needs of accurate human-computer interaction, automatic fatigue driving monitoring, intellient and efficient classroom and other amusive tasks. The research and application of facial expression recognition based on deep learning has attracted the attention of researchers at home and abroad and related commercial and technological personnel. However, there is still room for optimizing the structure and loss function of the deep convolution learning network for facial expression recognition. Therefore, the deep convolution neural network with more optimized characteristics is needed in facial expression recognition, so the propotions above can be improved. In this paper, compared with the existing deep convolution neural network optimization in facial expression recognition, these shortcomings are studied in this paper. The training data set named fer2013 is used to training convolutional network. The final results show that the method used in this paper can get a good recognition effect on facial expression recognition.