Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM62457
Volume:
10 |
5 |
May 2026
Pages:
1-14
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Computer science
IIMT COLLEGE OF ENGINEERING
Computer science
IIMT COLLEGE OF ENGINEERING
Computer science
IIMT COLLEGE OF ENGINEERING
Computer science
IIMT COLLEGE OF ENGINEERING
Computer science
IIMT COLLEGE OF ENGINEERING
The AI-Based Face Attendance System is an advanced biometric solution designed to automate attendance using real-time facial recognition. The system captures and processes facial images through deep learning models such as MTCNN and FaceNet, ensuring fast and highly accurate identification. By eliminating manual roll calls and preventing proxy attendance, it significantly improves transparency and reduces human effort. Developed using Python, OpenCV, and a centralised database, the system enables secure attendance storage, instant verification, and automated report generation. This AI-driven approach enhances efficiency, ensures contactless authentication, and modernises traditional attendance management across institutions. The proposed system captures live video through a webcam, detects faces using the MultiTask Cascaded Convolutional Network (MTCNN), and extracts 128-dimensional face embeddings using FaceNet. These embeddings are compared against stored embeddings using Euclidean distance to verify identity. Upon successful recognition, attendance is automatically recorded in a MySQL database with date, time, and session information. The system prevents duplicate entries and generates automated reports for administrative use.
KEYWORDS
The AI-Based Face Attendance System successfully demonstrates the application of deep learning and computer vision for automating attendance management. The system achieves high detection and recognition accuracy using MTCNN and FaceNet, operates in real time on standard hardware, and provides a secure, contactless alternative to traditional attendance methods. Key achievements of the project include: real-time face detection and recognition from live video; automated attendance recording with duplicate prevention; secure database storage with encryption; web-based administrative interface for monitoring and reporting; and scalable architecture suitable for institutional deployment.
1. TensorFlow Documentation: https://www.tensorflow.org/ 2. OpenCV Documentation: https://docs.opencv.org/ 3. DeepFace Library: https://github.com/serengil/deepface 4. MTCNN Implementation: https://github.com/ipazc/mtcnn 5. Flask Documentation: https://flask.palletsprojects.com/ 6. MySQL Documentation: https://dev.mysql.com/doc/ 7. Labeled Faces in the Wild: http://vis-www.cs.umass.edu/lfw/ 8. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 9. Computer Vision and Pattern Recognition (CVPR) Conference Proceedings 10. International Conference on Learning Representations (ICLR)
Publication Date
5/5/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
7
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...