Bank Locker Security System with Face and Liveness Detection

Abstract

This paper proposes a secure bank locker system using face recognition technology with liveness detection to avoid spoofing attacks. In the proposed system, a Convolutional Neural Network (CNN) is used for face recognition to verify the identity of the user. Blink detection and texture analysis are also used to confirm the presence of a live user. The Raspberry Pi is used for the implementation of the electronic lock mechanism.

Introduction

The text describes the design and development of a secure bank locker authentication system that replaces traditional access methods like keys, PINs, and cards with a biometric-based solution combining facial recognition and liveness detection.

The main motivation is that conventional locker security methods are vulnerable to theft, duplication, and misuse, while basic facial recognition alone can be tricked using photos, videos, or masks. To address this, the proposed system integrates two key components: a CNN-based facial recognition module to identify authorized users, and a liveness detection module that verifies the user is physically present by analyzing eye blinks, facial movements, and texture cues.

The system is designed to run on embedded hardware such as a Raspberry Pi connected to an electronic solenoid lock. Once a user approaches the locker, a camera captures their face, the system extracts facial features for identity verification, and simultaneously performs liveness detection. Access is granted only if both checks are successful; otherwise, the attempt is denied and logged for security monitoring.

The literature review highlights the evolution from traditional face detection methods (like Viola–Jones) to modern deep learning approaches (such as MTCNN and CNN-based anti-spoofing techniques), along with increasing integration of IoT systems for smart security applications. It also emphasizes the growing importance of liveness detection to prevent presentation attacks.

Conclusion

The integrated face recognition and liveness detection system offers high accuracy, security, and practical real-time performance. Performance metrics indicate that the system is suitable for use in bank lockers and other high-security physical access applications. The Bank Locker Security System with Face and Liveness Detection, as proposed, offers secure and contactless access through an integration of face recognition technology, which uses deep learning, and liveness detection.

References

[1] S. Z. Li and A. K. Jain, Handbook of Face Recognition, 2nd ed. London, U.K.: Springer, 2011. [2] A. George and S. Marcel, “Presentation attack detection using convolutional neural networks,” IEEE Transactions on Information Forensics and Security, vol. 14, no. 8, pp. 2147–2160, Aug. 2019. [3] K. Zhang, Z. Zhang, Z. Li, and Y. Qiao, “Joint face detection and alignment using multitask cascaded convolutional networks,” IEEE Signal Processing Letters, vol. 23, no. 10, pp. 1499–1503, Oct. 2016. [4] N. Patel, P. Sharma, and R. Singh, “IoT-based smart locker system using facial recognition,” International Journal of Innovative Research in Computer and Communication Engineering, vol. 8, no. 6, pp. 5632–5638, 2020. [5] Y. Liu, A. Jourabloo, and X. Liu, “Learning deep models for face anti-spoofing: Binary or auxiliary supervision,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 389–398. [6] P. Viola and M. J. Jones, “Robust real-time face detection,” International Journal of Computer Vision, vol. 57, no. 2, pp. 137–154, 2004. [7] J. Galbally, S. Marcel, and J. Fierrez, “Biometric antispoofing methods: A survey in face recognition,” IEEE Access, vol. 2, pp. 1530–1552, 2014. [8] S. S. D’Souza, “Deep learning for secure biometric authentication systems,” International Journal of Computer Applications, vol. 176, no. 38, pp. 1–6, 2020. [9] M. Sanderson and B. C. Lovell, “Multi-region probabilistic histograms for robust and scalable identity inference,” in Proc. International Conference on Biometrics: Theory, Applications, and Systems (BTAS), 2009, pp. 1–8. [10] A. Mohanty, S. B. Ghosh, and R. K. Sharma, “Design and implementation of an enhanced security locker system using facial recognition and IoT,” International Journal of Advanced Research in Computer and Communication Engineering, vol. 9, no. 3, pp. 45–49, Mar. 2020.

Copyright

Copyright © 2026 Dr. Nikita Kulkarni, Prof. Ashwini Kamble, Sanket Morde, Omkar Somwanshi, Aditya Konda, Rahul Shingade. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.