A Classroom Attendance System with Anti-Spoofing Based on ResNet101 and ArcFace for Face Recognition
Journal of Intelligence and Knowledge Engineering · 2026-03 · 4 (1) · 42-47
DOI: 10.62517/jike.202604107 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Intelligence and Knowledge Engineering, 2026-03. Verfasst von Wang Yunxi. Die Arbeit nennt 13 Literaturangaben.
Abstract (Originalsprache)
Addressing the inefficiencies and susceptibility to proxy check-ins inherent in traditional classroom attendance methods, alongside the performance degradation of existing face recognition systems under complex classroom lighting conditions, this paper proposes an anti-spoofing classroom attendance system based on an improved ResNet101 architecture and the ArcFace loss function. Our approach enhances the model's ability to extract illumination-invariant features by embedding Convolutional Block Attention Modules (CBAM) and optimizes feature space distribution through a joint loss function strategy. To tackle the challenge of extreme classroom illumination, a dedicated face dataset encompassing varied lighting conditions was constructed for model fine-tuning. Experimental results demonstrate that the system obtains a recognition accuracy of 99.68% on the public LFW dataset and a significant improvement from 76.3% to 88.7% on our proprietary extreme illumination test set, compared to the baseline model. Integrated with an active liveness detection mechanism, the system successfully defended against all photo and video replay attacks. Coupled with a developed web management platform, this system realizes an efficient, reliable, and non-contact automated attendance solution for teaching practice, providing a key technological framework for the development of smart classrooms.
Zitieren
APA
Yunxi, W. (2026). A Classroom Attendance System with Anti-Spoofing Based on ResNet101 and ArcFace for Face Recognition. Journal of Intelligence and Knowledge Engineering, 4(1), 42-47. https://doi.org/10.62517/jike.202604107
Vancouver
Yunxi W. A Classroom Attendance System with Anti-Spoofing Based on ResNet101 and ArcFace for Face Recognition. Journal of Intelligence and Knowledge Engineering. 2026;4(1):42-47. doi:10.62517/jike.202604107
BibTeX
@article{Yunxi2026,
author = {Yunxi, Wang},
title = {A Classroom Attendance System with Anti-Spoofing Based on ResNet101 and ArcFace for Face Recognition},
journal = {Journal of Intelligence and Knowledge Engineering},
year = {2026},
volume = {4},
number = {1},
pages = {42--47},
doi = {10.62517/jike.202604107}
}
EUVIMED