Expression Recognition of Classroom Children’s Game Video Based on Improved Convolutional Neural Network

Abstract

Humans express emotions in many ways, such as gestures, limbs, and expressions. Among them, facial expressions are the most intuitive way to express human inner emotional activities in human-to-human communication. With the rapid development of computer vision, facial expression recognition is an important research topic in the field of computer vision. It plays a key role in nonverbal communication and can be applied to human-computer interaction, social robotics, video games, and other fields. Traditional expression recognition algorithms require complex manual feature extraction, which takes a long time, and the accuracy of expression recognition in complex scenes is not high. However, with the development of deep learning, especially the convolutional neural network, facial expression recognition technology has also developed rapidly, and the recognition accuracy has been greatly improved. This paper studies the facial expression recognition method of classroom children’s game video based on convolutional neural network and proposes a convolutional neural network with deeper layers. The full connection is modified to 4 layers of convolution, 4 layers of pooling, and 2 layers of full connection. Firstly, the facial expression image is preprocessed by, for example, key point location, face cropping, and image normalization; then, the convolutional layer is used to extract the low-dimensional and high-dimensional feature information of the face image; and the pooling layer is used to extract the face image. The feature information is dimensionally reduced. Finally, the softmax classifier is used to classify and recognize the expressions of the training sample images. In order to improve the accuracy of expression recognition, a self-made set of labeled pictures was added to the expression training set. Simulation and comparison experiments show that the improved model has higher accuracy and smoother loss curve, which verifies the effectiveness of the improved network.