Authors : Rachel Adefunke Oladejo; Opeolorun Emmanuel Oloyede

Volume/Issue : Volume 11 - 2026, Issue 1 - January

Google Scholar : https://tinyurl.com/mrz45rcy

Scribd : https://tinyurl.com/m9zzz97z

DOI : https://doi.org/10.38124/ijisrt/26jan1037

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Attendance management is a critical administrative task in educational institutions. Traditional manual methods are often time-consuming, prone to human error, and lack real-time monitoring capabilities. To mitigate these challenges, this study proposes a robust, non-intrusive solution through the development of a real-time automated attendance system powered by state-of-the-art computer vision models. The proposed architecture utilizes a RetinaFace detector for precise facial localization and an ArcFace model with a ResNet-100 backbone to extract 512-dimensional biometric embeddings. To facilitate real-time deployment, the system is integrated into a Flask-based web framework, enabling asynchronous communication between the client-side camera interface and the recognition engine. A core contribution of this research is the implementation of a "best-face" short-circuit policy and a server-side temporal deduplication logic within an SQLite database, ensuring each individual is recorded only once per course. Experimental results indicate a high degree of reliability, achieving a 98.6% overall accuracy, 99.2% precision, and an F1-score of 98.5%. The system maintains an end- to-end processing latency of 407 ms on standard CPU hardware, demonstrating its viability for real-time applications without specialized infrastructure. Despite a minor validation gap attributed to environmental illumination, the study concludes that a 0.30 cosine distance threshold provides a robust operational balance for secure and efficient identity verification.

Keywords : Student Attendance System, Biometrics, Computer Vision, Real-Time Monitoring, DeepFace, ArcFace, RetinaFace, Flask API, SQLite.

References :

1. Ahmad, S., Khan, M. Z., & Alam, M. S. (2022). Limitations of RFID-based attendance systems in higher education: A security perspective. Journal of Educational Technology Systems, 51(2), 145-160.
2. Ahmed, S., Rahman, M. M., Hossain, M. A., & Hasan, M. K. (2022). Real-time student attendance system using computer vision and deep learning techniques. Journal of King Saud University – Computer and Information Sciences, 34(8), 5678–5690.
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 (CVPR) (pp. 4690-4699).
4. Deng, J., Guo, J., Zhou, Y., Yu, J., Kotsia, I., & Zafeiriou, S. (2020). RetinaFace: Single-shot multi-level face localisation in the wild. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 5203-5212).
5. Dev, K., & Patnaik, L. M. (2020). Automated attendance monitoring system using RFID and biometrics. International Journal of Advanced Computer Science and Applications, 11(3), 220–227.
6. Jain, V., Gupta, A., & Khanna, P. (2021). Automated attendance systems: A review of deep learning techniques. Expert Systems with Applications, 183, 115-132.
7. Nurkhamid, M., Prasetyo, E., & Nugroho, A. (2021). Intelligent attendance system using facial recognition. International Journal of Interactive Mobile Technologies, 15(9), 120–132.
8. Pei, Z., Huang, Y., & Liu, J. (2019). Deep learning-based face recognition for automatic attendance system. IEEE Access, 7, 123456–123465.
9. Sanli, S., & Ilgen, O. (2018). Camera-based automatic attendance system using face recognition. Procedia Computer Science, 132, 401–408.
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 (CVPR) (pp. 815-823).
11. Serengil, S. I., & Ozpinar, A. (2020). LightFace: A hybrid deep face recognition framework. In 2020 Innovations in Intelligent Systems and Applications Conference (ASYU) (pp. 1-5). IEEE.
12. Sethy, P. K., Barpanda, N. K., & Biswas, S. (2022). Automatic attendance system using face recognition and deep learning. Multimedia Tools and Applications, 81, 31245–31262.
13. Srivastava, S. (2023). Post-pandemic biometric trends: The shift from contact to non-contact systems. International Journal of Biometrics, 15(1), 22-40.