Classroom Attendance Auto-management Based on Deep Learning

DOI

10.2991/icesame-17.2017.327How to use a DOI?

Keywords

classroom evaluations, attendance, face detection, face recognition.

Abstract

Attendance is an important part of daily classroom evaluation. This paper develops an automatic attendance system by integrating two deep learning algorithm Faster R-CNN face detection algorithm and SeetaFace face recognition algorithm. The results of numerous experiments indict that: (1) 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. (2) For small classrooms with length of less than 6 meters, 1080P classroom monitoring video can meet the needs of classroom attendance; but for 9 meters of big classrooms, you should use 4K classroom surveillance video.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Dan Wang
AU  - Rong Fu
AU  - Zuying Luo
PY  - 2017/06
DA  - 2017/06
TI  - Classroom Attendance Auto-management Based on Deep Learning
BT  - Proceedings of the 2017 2nd International Conference on Education, Sports, Arts and Management Engineering (ICESAME 2017)
PB  - Atlantis Press
SP  - 1523
EP  - 1528
SN  - 2352-5398
UR  - https://doi.org/10.2991/icesame-17.2017.327
DO  - 10.2991/icesame-17.2017.327
ID  - Wang2017/06
ER  -