Children's Emotion Recognition Based on Convolutional Neural Network

In this paper, a facial expression recognition model for children was presented. Based on the existing research, this study divides common learner emotions into happiness, concentration, panic and boredom, and builds a large-scale learner emotion database based on this, and proposes a child emotion recognition method based on deep learning. Compared with traditional learner emotion recognition methods, this method has higher accuracy and robustness.