Abstract :

Face-based Attendance Systems Are Widely Adopted Because They Automate Identity Verification And Reduce Manual Record Keeping. However, Conventional Facial Recognition Systems Remain Susceptible To Presentation Attacks Such As Printed Photographs, Replay Videos, And Mobile Screen Images, Which Can Result In Unauthorized Attendance Marking. This Paper Presents A CNNbased Anti-spoofing Face Attendance Framework That Combines Robust Facial Authentication With Real-time Attendance Management. The Proposed Approach Performs Image Preprocessing Using YCrCb And CIE Luv* Colour Spaces To Extract Discriminative Histogram Features That Effectively Separate Genuine Facial Characteristics From Spoof Artefacts. These Features Are Supplied To A Convolutional Neural Network (CNN) For Live Face Verification Before The Recognition Stage. Once A Face Is Confirmed As Genuine, Facial Embeddings Are Generated And Matched With Registered User Encodings To Identify Individuals Accurately. A Web-based Application Has Been Developed With Modules For Administrator Authentication, User Registration, Secure Attendance Marking, Attendance Monitoring, And User Management. Attendance Records Are Automatically Stored In A MySQL Database With Corresponding Date And Time Information For Future Reference. Experimental Evaluation Demonstrates That The Proposed Framework Successfully Distinguishes Real Faces From Spoof Attempts While Maintaining Reliable Recognition Performance Under Practical Operating Conditions. The Integration Of Anti-spoofing Verification With Automated Attendance Management Provides A Secure, Efficient, And Scalable Solution Suitable For Educational Institutions, Workplaces, And Other Access-controlled Environments.

Published:

30-7-2026

Issue:

Vol. 26 No. 7 (2026)

Page Nos:

1323-1328

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite