Video Assisted Face Recognition in Smart Classroom

Student recognition in smart classrooms is challenging due to low resolution, occlusions, and various face orientations. We propose a video-based approach for robust face recognition. It firstly collects a continuous sequence of face images through inter-frame analysis. Then, it aggregates face features, via statistical elimination of outliers. We introduce a new consistency loss to address varying face resolutions, enabling the learning of scale-robust features. Experimental results demonstrate that our proposed approach improves recognition performance under various conditions compared to previous methods. In our experiments, it achieved the highest recognition accuracy (83.57%) for 8×8 resolution cases.

I. Introduction

Students occasionally experience distractions, confusion, or lack of interest during the learning process, which makes it challenging for teachers to assess student engagement promptly. Consequently, there is an urgent need for technological interventions to assist teachers in their instructional efforts. One crucial requirement in the context is the accurate identification of students. However, the low quality of images captured by cameras, particularly in large classrooms, presents a significant obstacle to accurate face recognition.