Submit

Login Login

Register Register

Home / Journals / CMC / Online First / doi:10.32604/cmc.2026.072054
Journal Menu
Special Issues
Table of Content

All issues

Online First

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Open Access

ARTICLE

Securing Restricted Zones with a Novel Face Recognition Approach Using Face Feature Descriptors and Evidence Theory

Rafika Harrabi1,2,*, Slim Ben Chaabane1,2, Hassene Seddik2
1 Department of Computer Engineering, Faculty of Computers and Information Technology, University of Tabuk, Tabuk, Saudi Arabia
2 Laboratoire de Robotique Intelligente, Fiabilité Et Traitement du Signal Image (RIFTSI), ENSIT-Université de Tunis, Tunis, Tunisia
* Corresponding Author: Rafika Harrabi. Email: email

Computers, Materials & Continua https://doi.org/10.32604/cmc.2026.072054

Received 18 August 2025; Accepted 29 September 2025; Published online 04 February 2026

Abstract

Securing restricted zones such as airports, research facilities, and military bases requires robust and reliable access control mechanisms to prevent unauthorized entry and safeguard critical assets. Face recognition has emerged as a key biometric approach for this purpose; however, existing systems are often sensitive to variations in illumination, occlusion, and pose, which degrade their performance in real-world conditions. To address these challenges, this paper proposes a novel hybrid face recognition method that integrates complementary feature descriptors such as Fuzzy-Gabor 2D Fisher Linear Discriminant (FG-2DFLD), Generalized 2D Linear Discriminant Analysis (G2DLDA), and Modular-Local Binary Patterns (Modular-LBP) with Dempster–Shafer (DS) evidence theory for decision fusion. The proposed framework extracts global, structural, and local texture features, models them using Gaussian distributions to estimate belief factors, and fuses these belief factors through DS theory to explicitly handle uncertainty and conflict among descriptors. Experimental validation was performed on two widely used benchmark datasets, ORL and Cropped Yale B, achieving recognition rates exceeding 98%, which outperform traditional methods as well as recent deep learning-based approaches. Furthermore, the method demonstrated strong robustness under noisy conditions, maintaining accuracies above 96% with salt-and-pepper and Gaussian noise. These results highlight the effectiveness of the proposed integration strategy in enhancing accuracy, reliability, and resilience compared to single-descriptor and conventional fusion methods. Given its high performance and efficiency, the proposed method shows strong potential for deployment in real-world restricted-zone applications such as smart parking systems, secure facility access, and other high-security domains.

Keywords

Face recognition; feature extraction; FG-2DFLD; G2DLDA; Modular-LBP; evidence theory; mass function; gaussian distribution; classification

  • 61

    View

  • 12

    Download

  • 0

    Like

Related articles
Copyright© 2026 Tech Science Press
© 1997-2026 TSP (Henderson, USA) unless otherwise stated

Share Link