Towards Seamless Attendance Monitoring: A ML-Driven Real-Time Facial Recognition System for Automated Class Attendance

• Author(s): Ugbana C. Kelvin ; Tamuno-Omie J. Alalibo ; Nkolika O. Nwazor
• Paper ID: 1710382
• Page: 42-52
• Published Date: 02-09-2025
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 9 Issue 3 September-2025

Abstract

Conventional attendance recording methods, are susceptible to delays, impersonation, and hygiene concerns. This paper presents a real-time attendance monitoring system tailored for educational environments where accuracy, and record integrity are essential. The proposed system integrated a CNN-SVM-based facial recognition model with a pan/tilt servo-controlled camera to enable dynamic coverage and continuous subject tracking. The hardware setup comprises a Raspberry Pi 5 as the main processor, an IR night-vision camera for reliable capture in varying light, an Arduino Nano for servo actuation, and a dual-axis servo platform for camera mobility. On the software side, Python, Dlib, OpenCV, and OpenFace support facial detection and embedding. The model, trained on multiple samples per student, was optimized for offline execution to ensure privacy, speed, and secure local storage. The system achieved a recognition accuracy of 96.8% with an average inference time of 0.79 milliseconds per instance. Field validation in real classroom environments confirmed consistent performance under motion and low-light scenarios, with automated attendance sheets generated by associating recognized identities with corresponding timestamps. Leveraging deep learning and embedded processing, the system provides a portable, hygienic, and efficient alternative to traditional attendance methods, enhancing classroom management, data integrity, and scalability.

Keywords

Automated attendance, facial recognition, real-time tracking, classroom monitoring, Raspberry Pi.

Citations

IRE Journals:
Ugbana C. Kelvin , Tamuno-Omie J. Alalibo , Nkolika O. Nwazor "Towards Seamless Attendance Monitoring: A ML-Driven Real-Time Facial Recognition System for Automated Class Attendance" Iconic Research And Engineering Journals Volume 9 Issue 3 2025 Page 42-52

IEEE:
Ugbana C. Kelvin , Tamuno-Omie J. Alalibo , Nkolika O. Nwazor "Towards Seamless Attendance Monitoring: A ML-Driven Real-Time Facial Recognition System for Automated Class Attendance" Iconic Research And Engineering Journals, 9(3)