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 5 (September-October 2026) Submit your research before last 3 days of October to publish your research paper in the issue of September-October.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 8 Issue 5
September-October 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

GeoSecure-FR: A Geofenced, Occlusion-Aware Face Recognition Framework for Proximity-Based Attendance and Access Verification

Author(s) Mr. Pradeep Kumar, Prof. Indumathy M
Country India
Abstract Attendance systems that match a face against a gallery answer the wrong question. They ask whether an image resembles an enrolled person, not whether a live, visible, enrolled person is at the venue. This paper presents GeoSecure-FR as a rejection cascade for that problem. A phone sends its GPS fix. The method arms the camera only when the Haversine distance to the venue centre is inside a configured radius plus a GPS slack. A captured frame must then clear a visibility check. The serving liveness gate samples a short frame window. While a recapture remains, a missing blink stops the attempt before recognition. The liveness flag is the disjunction of a detected blink and a MobileNetV2 score of at least 0.80, and only the last window is accepted or rejected by that flag. The first failure stops the chain, and the log stores the failing stage. On the AT&T face set, the rank-1 result for the matcher alone is 1.000 for ArcFace against 0.865 for an Eigenfaces baseline under the same protocol. That comparison does not pass the frame through the geofence, the visibility gate, or liveness. A lower-face blackout rule, added after three weaker rules failed, rejects 200 of 200 synthetically masked probes and none of 400 clean frames. Retraining the liveness model on a CelebA-Spoof subset moves two screen-replay scores from 0.986 and 0.968, both false accepts, to 0.035 and 0.121 at a live threshold of 0.80. CPU end-to-end latency remains about 4–7 s, above a 3 s target. These figures show the sample and the condition behind each number. They do not show a presentation-attack rate, a real-mask rate, room-level location, or a latency below 3 s.
Keywords Face Recognition, Geofencing, Occlusion, Liveness Detection, Attendance, Access Control
Field Computer
Published In Volume 8, Issue 5, September-October 2026
Published On 2026-10-03
DOI https://doi.org/10.36948/ijfmr.2026.v08i05.88962
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