A Facial Expression Recognition System for Smart Learning Based on YOLO and Vision Transformer

This paper proposes a facial expression recognition system for smart learning on classroom. Firstly, YOLO is used to extract face images of multiple students from high-resolution video; secondly, face images are preprocessed, then a self-attention based model named Vision Transformer (ViT) is used to recognize facial expressions; finally, the classified facial expression is used to assist teacher to analyze students’ learning status, so as to provide suggestions for improving teaching effect.