Automatic Attendance Face Recognition for Real Classroom Environments

This paper selects Faster R-CNN target detection algorithm and SeetaFace Face recognition algorithm. Firstly introduce deep learning technology to multi-face detection in real classrooms, and the experimental results of the two algorithms are verified. Secondly, Based on the Faster R-CNN face detection algorithm and SeetaFace face recognition algorithm, a complete prototype of attendance system is constructed, and five types of attendance indicators are defined. Attendance tables reflecting the attendance status of students are designed. Finally, experiments are conducted based on the class attendance system. The system can record such five violations of classroom, that is absence, later arrival, early departure, free access, and carelessness for attendance, and give the attendance table which can reflect the learning situation of all students after school.