International Journal For Multidisciplinary Research

E-ISSN: 2582-2160   •   Impact Factor: 9.24

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 8, Issue 4 (July-August 2026) Submit your research before last 3 days of August to publish your research paper in the issue of July-August.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 8 Issue 4
July-August 2026

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scirus Scribd Semantic Scholar UTeM - Universiti Teknikal Malaysia Melaka Wiki for Call for Papers WorldCat Zenodo

Adaptive Multi-Model LBPH with Temporal Stability Validation for Real Time Attendance Recognition

Author(s) Aaqib Rashid Mir, Ridwan Uz Zaman Pandit, Snehal Dileep Guruphale, Athira Pradeep K, Ashish Kumar, Sumit Kumar Pushkar
Country India
Abstract Attendance management in educational institutions is a critical administrative function that is traditionally prone to errors, time inefficiency, and proxy fraud. This paper proposes an Adaptive Local Binary Pattern Histogram (LBPH) framework for a real-time, face-based attendance management system. Unlike conventional single-model LBPH approaches, the proposed system trains three LBPH classifiers using distinct radius configurations (radius = 1, 2, 3) to
enable multi-scale facial feature extraction. An ensemble-based decision mechanism combining majority voting and average confidence scoring is applied to the outputs of all three models. A threshold-based filter (confidence ≤ 110)
guards against false acceptance of unknown faces, while a frame-based stability validator requires the same identity to be confirmed across three consecutive webcam frames before attendance is recorded. The system is built on Python,
OpenCV, Tkinter, and MySQL, and operates entirely on standard CPU hardware without GPU requirements. Experimental results on a six-student cohort demonstrate a recognition accuracy of 94%, a 7-percentage-point improvement over single-model LBPH (87%) and a 3-percentage-point improvement over an un-stabilized multi-model variant (91%), while sustaining an average end-to-end recognition latency of 41 ms per frame on commodity CPU hardware. The proposed solution provides a practical, contactless, and reliable attendance management system suitable for real-world deployment in resource-constrained educational institutions.
Keywords Adaptive LBPH, face recognition, attendance management, Haar Cascade, ensemble learning, stable frame validation, OpenCV
Field Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In Volume 8, Issue 4, July-August 2026
Published On 2026-07-19
View / Download PDF File

Share this



E-ISSN 2582-2160
CrossRef

CrossRef DOI prefix of IJFMR is 10.36948/ijfmr

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About IJFMR
Fees & Payment
Current Issue
Publication Archive 		Submit Research Paper
Track Submission Status
Publication Guidelines
Publication Ethics
Peer Review & Plagiarism 		Join as a Reviewer
Editors & Reviewers
Reviewer Referral Program
Get Reviewer Membership Certi. 		Website/Journal Policies
Usage Policy
Content Policies
Privacy Policy
Contact Us +91-9687-828-838 editor@ijfmr.com
Powered by Sky Research Publication and Journals