Deep Learning-Based Facial Attendance Tracker

Abstract

To develop a real-time face attendance recognition system that utilizes facial recognition technology, integrated with advanced anti-spoofing techniques. This approach ensures a secure, contactless method for marking attendance, significantly reducing the risk of unauthorized or fraudulent entries. The system aims to identify and prevent spoofing attempts, such as the use of photos, pre-recorded videos, or masks, during the authentication process.The core functionality involves processing real-time video input, detecting faces frame-by-frame, and accurately matching them with a pre-registered database. This enables automatic attendance marking without the need for manual intervention. The system is designed to deliver high accuracy and reliability, ensuring that only verified individuals are recorded for attendance purposes. To provide a user-friendly and adaptable solution suitable for various environments and institutions, the system is designed to minimize manual errors while enhancing overall security. Furthermore, it is scalable and can be easily implemented across different sectors, including educational institutions, corporate offices, and other organizations, enabling efficient and accurate attendance management.

Introduction

In response to the limitations of traditional attendance systems, a real-time facial recognition-based attendance system is proposed. This system uses contactless technology to enhance efficiency, security, and accuracy in environments like schools and organizations.

Key Features:

• Face Detection & Recognition: Utilizes a CNN-based algorithm to detect faces and compare them against a registered database.

• Anti-Spoofing Measures: Integrates liveness detection, blink detection, and texture analysis to prevent spoofing with photos, videos, or masks.

• Real-Time Processing: Attendance is recorded instantly upon successful face verification.

• User-Friendly Interface: Admins can take attendance or register new users through an intuitive dashboard.

• Scalability: Designed for easy deployment and use in large-scale institutional settings.

System Workflow:

1. User faces webcam.

2. System performs face detection and liveness check.

3. If verified, face is recognized and matched to the database.

4. Attendance is marked and logged automatically.

5. Admin can also register new users with their data and face image.

Outputs & Interface:

• Admin login and dashboard for system management.

• Dataset collection for model training.

• Attendance report interface showing names, timestamps, and status.

Conclusion

In conclusion, The development of a real-time face attendance recognition system integrated with advanced anti-spoofing techniques provides a secure, efficient, and contactless solution for attendance management. By leveraging facial recognition technology and real-time video processing, the system successfully automates the attendance marking process, eliminating the need for manual intervention and significantly reducing the risk of fraudulent entries. The implementation of anti-spoofing mechanisms effectively detects and prevents spoofing attempts such as printed photos, video replays, or masks, ensuring the authenticity of user verification. The modular interface, including employee management, training, embedding extraction, and reporting, enhances usability and scalability across various sectors like educational institutions and corporate organizations. This system not only improves operational accuracy and security but also demonstrates adaptability for broader applications. Overall, the proposed solution offers a reliable and intelligent alternative to traditional attendance systems, promoting digital transformation while ensuring data integrity and user authenticity in attendance tracking processes.

References

[1] AdityaMehrotra, Christian Giang, NoéDuruz, JulienDedelley, Andrea Mussati, Melissa Skweres, and Francesco Mondada (2020), “Introducing a Paper-Based Programming Language for Computing Education in Classrooms,” In Proceedings of the 2020 ACM Conference on Innovation and Technology in Computer Science Education (ITiCSE \'20), Association for Computing Machinery, New York, NY, USA, 180–186, pp. 180-186, 2020.Antonio Lazaro, David Girbau, Marc Lazaro, and Ramon Villarino, “Seat-Occupancy Detection System and Breathing Rate Monitoring Based on a Low-Cost mm-Wave Radar at 60 GHz” in IEEE Access, vol. 9, pp. 115403-115414, August 2021. [2] Chen, Hsi-min, Nguyen, Bao-an, Yan, Yi-xiang, Dow, Chyi-Ren (2020), \"Analysis of Learning Behavior in an Automated Programming Assessment Environment A Code Quality Perspective\" in Computers and Information Processing on IEEE, Vol. 8, pp. 167-342, September 2020. (HMC, BAN, YXY, CRD). [3] Govindarajan, Kannan, Kumar, Vivekanandan Suresh, Kinshuk (2016), \"Dynamic Learning Path Prediction – A Learning Analytics Solution,\" in 8th International Conference on Technology for Education on IEEE, pp. 188-193, 2016. (KG, VSK, K). [4] Chaudhary, Nishit, DarshThakkar, Divya Patel, Keyurkumar Patel, PrathamSavaliya, and ArmaanMistry. \"Advance Public Bus Transport Management System: An Innovative Smart Bus Concept.\" In 2024 IEEE International Conference on Consumer Electronics (ICCE), pp. 1-6. IEEE, 2024. [5] Li, Nianfeng, Shen, Xiangfeng, Sun, Liyan, Xiao, Zhiguo, Ding, Tianjiao, Li, Tiansheng, Li, Xinhang (2023), \"Dodona Chinese Face Dataset for Face Recognition in an Uncontrolled Classroom Environment,\" Vol. 11, pp. 86963-86976. (NL, XS, LS, ZX, TD, TL, XL). [6] Li, X.H.J., Wang, Y.C. (2022), \"Face Recognition and Anti-Spoofing Challenges and Future Directions,\" IEEE Signal Processing Magazine, Vol. 39, pp. 45-58. (XHJL, YCW). [7] Liu, H.R.R.D.M.D.K., Chen, J.Y. (2021), \"Face Recognition in Unconstrained Environments A Study on Robustness,\" IEEE Transactions on Multimedia, Vol. 23, pp. 2203-2215. (HRRDMKD, JYC). [8] Rahman, K.K.M.Z.I., Al-Sharif, R.A., Khan, M.A. (2022), \"A Survey on Face Recognition Techniques and Applications,\" IEEE Communications Surveys & Tutorials, Vol. 24, pp. 1230-1254. (KKMZI, RAA, MAK). [9] Sharma, P.S.A.K.V.D., Joshi, R.B. (2022), \"Synchronized Face Recognition Using Deep Learning,\" IEEE Transactions on Image Processing, Vol. 31, pp. 6724-6736. (PSAKVD, RBJ). [10] Wang, F.T.M.H.X., Li, M.L. (2021), \"Performance Evaluation of Face Recognition Systems with Anti-Spoofing Measures,\" IEEE Transactions on Neural Networks and Learning Systems, Vol. 32, pp. 1003-1015. (FTMHXW, MLL).

Copyright

Copyright © 2025 Mr. M. Arulselvan, M. Abishek, J. R. S. Abizeeth, M. Hari Balamurugan, N. M. R. Harrish Nandha. 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.