(Retracted) Facial expression recognition in classroom environment based on improved Xception model

Abstract

Nowadays, there is a large amount of research on facial expression, and researchers have put forward a variety of effective methods. Now, due to the unsupervised learning function, deep learning is increasingly applied to facial expression recognition. The purpose of this paper is to study the recognition of facial expressions in a classroom environment based on an improved anomaly model. This paper proposes a new face recognition model, which is based on convolutional neural network. This paper introduces the construction and algorithm of the model and tests its performance for expression recognition through experiments. The experimental results show that the expression recognition accuracy of the facial expression recognition model proposed is 72.4%. The experiment compares this model with other models, the recognition accuracy of the proposed model architecture is 72.4%, and finds that this model has the best classification accuracy and the least parameters.