Employee Attendance System Based on Face Recognition and Liveness Detection Using MagFace

Face recognition-based attendance systems are vulnerable to spoofing attacks without effective liveness detection. This study proposes an employee attendance system that integrates CNN-based liveness detection with MagFace-based face recognition to enhance security. The liveness module serves as a preliminary filter to distinguish live faces from spoof attempts before identity verification. Experimental results show that the liveness detection module achieved accuracies of 98%, 96.28%, and 87.27% on training, validation, and testing datasets, respectively, with a False Positive Rate (FPR) of 6.0% on the testing dataset. The MagFace-based recognition module achieved an accuracy of 95.24%, with a False Acceptance Rate (FAR) of 4.64% and an Equal Error Rate (EER) of approximately 4.76%. These results indicate that the proposed system is suitable for employee attendance applications. However, the liveness detection module is intended as a baseline prototype and is not yet designed for high-security biometric authentication scenarios.

Keywords: ArcFace, Face Recognition, Attendance System

[1] Q. Meng, S. Zhao, Z. Huang, and F. Zhou, “MagFace: A Universal Representation for Face Recognition and Quality Assessment,”

Proc. IEEE/CVF CVPR, pp. 14225–14234, 2021.

[2] Z. Yu, G. Chen, F. Liu, et al., “Deep Learning for Face Anti-Spoofing: A Survey,” IEEE Trans. PAMI, 2021.

[3] P. Terhörst, A. B. Abtahi, and J. Kittler, “QMagFace: Simple and Accurate Quality-Aware Face Recognition,” IEEE/CVF WACV,

2023.

[4] A. Liu, H. Zhang, X. Li, et al., “FM-ViT: Flexible Modal Vision Transformers for Face Anti-Spoofing,” IEEE ICCV, 2023.

[5] K. Srivatsan, L. Chen, and M. Wang, “FLIP: Cross-Domain Face Anti-Spoofing with Language Guidance,” ICCV, 2023.

[6] K. Wang, H. Liu, and Z. Yan, “Multi-Domain Incremental Learning for Face Anti-Spoofing,” AAAI, 2024.

[7] J. Zhang, “UCDCN: Nested Central Difference Convolution for Face Anti-Spoofing,” Journal of Intelligent Manufacturing, 2024.

[8] A. Benlamoudi, M. Tairi, and S. El Saddik, “Deep Learning for Face Anti-Spoofing,” Sensors, vol. 22, no. 10, 2022.

[9] M. Pooshideh, A. Hadid, and R. R. Selvaraju, “Spoof Prevention Methods: A Systematic Review,” ACM Computing Surveys, 2024.

[10] J. T. Santoso, “Liveness Detection-Based Attendance System Using CNN,” JUITA, 2022.

[11] X. Wang, L. Chen, and Y. Li, “MobileFaceNet: Compact CNN for Mobile-Level Recognition,” arXiv, 2020.

[12] S. Deng, H. Liu, and K. Zhao, “Lightweight CNN for Real-Time Face Liveness Detection,” IEEE Access, vol. 9, 2021.

[13] R. Sun and M. Yang, “Face Recognition in Attendance Monitoring,” IJACSA, 2022.

[14] H. Nguyen and T. Tran, “Vision Transformer for Liveness Detection Generalization,” Pattern Recognition Letters, 2023.

[15] Y. Li and J. Zhang, “PatchNet Transformer for Anti-Spoofing,” CVPR Workshops, 2022.

[16] W. Wang and H. Zhao, “rPPG-Based Liveness Detection,” Frontiers in Signal Processing, 2023.

[17] Z. Huang and F. Zhou, “Quality-Aware Face Embedding Enhancement,” Pattern Recognition, 2022.

[18] B. Chen and R. Zhang, “Fourier Domain Face Spoof Detection,” IEEE BTAS, 2021.

[19] H. Wu, “Deepfake Liveness Detection Using Multimodal Fusion,” Information Fusion, 2024.

[20] Y. Li and J. Chen, “CelebA-Spoof Dataset,” ECCV, 2020.

[21] S. Yang and K. Wang, “Real-Time Face Attendance with Liveness Detection,” IEEE IoT Journal, 2023.

[22] S. Noor and A. Malik, “MagFace-Based Access Control System,” International Journal of Biometrics, 2023.

[23] H. Zhang and M. Xu, “Data Augmentation Strategies for Liveness Generalization,” Neurocomputing, 2022.

[24] L. Yuan and R. Li, “Mobile Deployment Optimization for Face Recognition,” IEEE Embedded Systems Letters, 2023.

[25] D. Kaur, “CNN-Based Live/Spoof Classification,” Applied Sciences, 2022.

[26] B. Lovejoy, “Here’s how Apple’s TrueDepth 3D camera works,” 9to5Mac, Nov. 16, 2017. [Online]. Available:

https://9to5mac.com/2017/11/16/truedepth-3d-camera-animation/