Abstract
Attendance management is a critical ad- ministrative task in educational institutions. Traditional attendance systems such as manual registers, RFID cards, and fingerprint biometrics suffer from several limitations including time consumption, proxy attendance, and lack of real-time analysis. This paper presents an AI-based smart attendance system that uses face recognition to automate attendance marking in higher education classrooms. The proposed system captures live video through a webcam, detects faces using Haar-cascade classifiers, and identifies students using 128-dimensional deep face embeddings. Attendance data are securely stored in a local SQLite database and analyzed using an analytics dashboard to visualize attendance trends. In addition, a lightweight rule-based emotion detection mod- ule classifies student expressions into Happy, Neutral, and Tired categories, providing insights into class- room engagement. The experimental evaluation con- ducted on a 50-student dataset achieved a recognition accuracy of 96.7% with an average processing time of approximately one second per frame, demonstrat ing the suitability of the system for real-world deployment.
Keywords
Smart Attendance; Face Recognition; Emotion Detection; Computer Vision; Artificial Intelligence; Student Analytics Smart Attendance; Face Recognition; Emotion Detection; Computer Vision; Artificial Intelligence; Student Analytics
Citations
IRE Journals:
Mahammad Sinan, Abdul Muneer, Muskan Khanum, Sharika Taskeen, Prof. Dr. Venkatesh T. "AI-Based Smart Attendance System Using Face Recognition" Iconic Research And Engineering Journals Volume 9 Issue 6 2025 Page 1201-1203 https://doi.org/10.64388/IREV9I6-1712913
IEEE:
Mahammad Sinan, Abdul Muneer, Muskan Khanum, Sharika Taskeen, Prof. Dr. Venkatesh T.
"AI-Based Smart Attendance System Using Face Recognition" Iconic Research And Engineering Journals, 9(6) https://doi.org/10.64388/IREV9I6-1712913
About IRE Journals
IRE Journals is an open access online journals established with an aim to publish high quality of research work in various diciplines. We have more than 6 years in publications. Over 2500+ papers already published.
Important Links
For Authors
Volume 8:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 7:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 6:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 5:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 4:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 3:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12