Home / Current Issue / Paper 1723595
AI Smart Attendence System Using Face Recognition
Subject area: Science,Engineering and Technology · Area of research: Artificial Intelligence, Machine Learning
DOI: 10.64388/IREV10I4-1723595
Abstract
Attendance is an essential academic activity, but conventional roll calls and manual records consume classroom time and may introduce recording errors and opportunities for proxy attendance. This paper presents an AI Smart Attendance System using face recognition that automates attendance through real-time camera processing and timetable-based validation. The implemented prototype is developed using Python and Streamlit with OpenCV, the face_recognition library, WebRTC camera streaming, SQLite, Pandas and Matplotlib. The system provides administrator and student authentication, student registration, section management, timetable checking, face-based attendance, multi-frame confirmation, duplicate-attendance prevention, security logging, attendance filtering, analytics and CSV reporting. The face verification workflow is configured to require multiple confirming frames before an attendance record is created. The proposed enhanced architecture extends the prototype with mobile access, GPS/geofencing, separate subject-teacher accounts and an HOD dashboard. Under this architecture, attendance is accepted only when the student's identity, scheduled subject and permitted location satisfy the configured rules. Teachers can monitor attendance for their assigned subjects, while the HOD can obtain department-level visibility across teachers, subjects, sections and students. The paper describes the system architecture, methodology, database design, security controls, implementation status and planned enhancements. Rather than claiming unmeasured accuracy or deployment results, the study identifies the measurable evaluation parameters required for future experimental validation.
Keywords
Artificial Intelligence, Face Recognition, Smart Attendance, Timetable Validation, WebRTC, SQLite, GPS Geofencing, Role-Based Access Control.
How to cite this paper
@article{1723595,
author = {Mohammed Muzammil, Muhammad Adam Khan, Mahammad Yunus B, Mir Naqi Raza, Bhagyashri Wakde; Soniya Komal V},
title = {AI Smart Attendence System Using Face Recognition},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {10},
number = {4},
pages = {202-210},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1723595.pdf},
abstract = {Attendance is an essential academic activity, but conventional roll calls and manual records consume classroom time and may introduce recording errors and opportunities for proxy attendance. This paper presents an AI Smart Attendance System using face recognition that automates attendance through real-time camera processing and timetable-based validation. The implemented prototype is developed using Python and Streamlit with OpenCV, the face_recognition library, WebRTC camera streaming, SQLite, Pandas and Matplotlib. The system provides administrator and student authentication, student registration, section management, timetable checking, face-based attendance, multi-frame confirmation, duplicate-attendance prevention, security logging, attendance filtering, analytics and CSV reporting. The face verification workflow is configured to require multiple confirming frames before an attendance record is created. The proposed enhanced architecture extends the prototype with mobile access, GPS/geofencing, separate subject-teacher accounts and an HOD dashboard. Under this architecture, attendance is accepted only when the student's identity, scheduled subject and permitted location satisfy the configured rules. Teachers can monitor attendance for their assigned subjects, while the HOD can obtain department-level visibility across teachers, subjects, sections and students. The paper describes the system architecture, methodology, database design, security controls, implementation status and planned enhancements. Rather than claiming unmeasured accuracy or deployment results, the study identifies the measurable evaluation parameters required for future experimental validation.},
keywords = {Artificial Intelligence, Face Recognition, Smart Attendance, Timetable Validation, WebRTC, SQLite, GPS Geofencing, Role-Based Access Control.},
month = {October},
doi = {https://doi.org/10.64388/IREV10I4-1723595}
}