Design and Implementation of a Face Recognition-Based Access Control System with Active Liveness Detection
Öz
Face recognition-based access control systems have gained significant attention due to their contactless operation, ease of deployment, and practical applicability in security-sensitive environments. However, the vulnerability of conventional face recognition systems to spoofing attacks, such as printed photographs and replayed videos, remains a major limitation. In this study, a real-time access control system enhanced with blink-based liveness detection is proposed and implemented to improve the security and reliability of biometric authentication. The developed framework integrates face detection, image preprocessing, 128-dimensional facial embedding extraction, Support Vector Machine (SVM)-based identity classification, Eye Aspect Ratio (EAR)-based blink analysis, and Arduino-assisted physical access control within a unified architecture. The system was evaluated using a custom dataset consisting of 300 facial images collected from six users under varying pose and illumination conditions. Experimental results showed that the proposed system achieved an overall face recognition accuracy of 95.7%, while the normal recognition scenario reached a success rate of 98%. The liveness detection module successfully prevented 96% of static photo attacks and 90% of replay-based attacks, demonstrating the effectiveness of blink-based verification as an additional security layer. In terms of computational performance, the system maintained real-time operability with acceptable response times on standard hardware. The findings indicate that the proposed low-cost and modular architecture provides a practical and efficient solution for secure access control applications. Furthermore, the study highlights that combining identity recognition with liveness verification significantly improves the robustness of face-based authentication systems against presentation attacks.
Anahtar Kelimeler
Face recognition, liveness detection, artificial intelligence, biometric security
Kaynakça
- [1] Ahonen, T., Hadid, A., & Pietikäinen, M. (2004, May). Face recognition with local binary patterns. In European conference on computer vision (pp. 469-481). Berlin, Heidelberg: Springer Berlin Heidelberg.
- [2] Yucer, S., Tektas, F., Al Moubayed, N., & Breckon, T. (2024). Racial bias within face recognition: A survey. ACM Computing Surveys, 57(4), 1-39.
- [3] 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).
- [4] Parkhi, O., Vedaldi, A., & Zisserman, A. (2015). Deep face recognition. In BMVC 2015-Proceedings of the British Machine Vision Conference 2015. British Machine Vision Association.
- [5] Soukupova, T., & Cech, J. (2016, February). Eye blink detection using facial landmarks. In 21st computer vision winter workshop, Rimske Toplice, Slovenia (Vol. 2, p. 4).
- [6] 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).
- [7] Li, Z., & Sun, H. (2023). Artificial intelligence-based spatio-temporal vision sensors: applications and prospects. Frontiers in Materials, 10, 1269992.
- [8] Lifelo, Z., Ding, J., Ning, H., & Dhelim, S. (2024). Artificial intelligence-enabled metaverse for sustainable smart cities: Technologies, applications, challenges, and future directions. Electronics, 13(24), 4874.
- [9] Boulkenafet, Z., Komulainen, J., & Hadid, A. (2016). Face spoofing detection using colour texture analysis. IEEE Transactions on Information Forensics and Security, 11(8), 1818-1830.
- [10] Gao, G., Wang, Y., Chen, Y., Yang, G., Yao, L., Zhang, X., ... & Li, G. (2024). An oriented ship detection method of remote sensing image with contextual global attention mechanism and lightweight task-specific context decoupling. IEEE Transactions on Geoscience and Remote Sensing, 63, 1-18.