A Classroom Attendance System with Anti-Spoofing Based on ResNet101 and ArcFace for Face Recognition

DOI: https://doi.org/10.62517/jike.202604107

Author(s)

Wang Yunxi

Affiliation(s)

Intelligence Science and Technology, Xidian University, Xi'an, China

Abstract

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.

Keywords

Face Recognition; Classroom Attendance; ResNet101; ArcFace; Attention Mechanism; Illumination Robustness

References

[1] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778). [2] Wang, H., Wang, Y., Zhou, Z., Ji, X., Gong, D., Zhou, J., ... & Liu, W. (2018). Cosface: Large margin cosine loss for deep face recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5265-5274). [3] Deng, J., Guo, J., Xue, N., & Zafeiriou, S. (2019). Arcface: Additive angular margin loss for deep face recognition. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 4690-4699). [4] Woo, S., Park, J., Lee, J. Y., & Kweon, I. S. (2018). Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV) (pp. 3-19). [5] Zhao, J., Cheng, Y., Xu, Y., Xiong, L., Li, J., Zhao, F., ... & Yan, S. (2018). Towards pose invariant face recognition in the wild. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2207-2216). [6] Zhu, Y., Lai, Z., Li, F., & Huang, Y. (2023). A laboratory attendance system based on face recognition. Internet of Things Technologies. [7] Guo, Y., Zhang, L., Hu, Y., He, X., & Gao, J. (2016). Ms-celeb-1m: A dataset and benchmark for large-scale face recognition. In European conference on computer vision (pp. 87-102). Springer, Cham. [8] Huang, G. B., Mattar, M., Berg, T., & Learned-Miller, E. (2008). Labeled faces in the wild: A database for studying face recognition in unconstrained environments. In Workshop on faces in'Real-Life'Images: detection, alignment, and recognition. [9] Taigman, Y., Yang, M., Ranzato, M. A., & Wolf, L. (2014). Deepface: Closing the gap to human-level performance in face verification. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1701-1708). [10] Schroff, F., Kalenichenko, D., & Philbin, J. (2015). Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 815-823). [11] Han, S., Mao, H., & Dally, W. J. (2015). Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149. [12] Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531. [13] Gilad-Bachrach, R., Dowlin, N., Laine, K., Lauter, K., Naehrig, M., & Wernsing, J. (2016). Cryptonets: Applying neural networks to encrypted data with high throughput and accuracy. In International conference on machine learning (pp. 201-210). PMLR.