Hybrid Approach for Face Recognition from a Single Sample per Person by Combining VLC and GOM

Ahmed Ghorbel,Walid Aydi,Nouri Masmoudi,Imen Tajouri

doi:10.1515/jisys-2018-0380

Ahmed Ghorbel, Walid Aydi + Show 2 more

Open Access

https://doi.org/10.1515/jisys-2018-0380

Copy DOI

Abstract

Abstract This paper proposes a new face recognition system based on combining two feature extraction techniques: the Vander Lugt correlator (VLC) and Gabor ordinal measures (GOM). The proposed system relies on the execution speed of VLC and the robustness of GOM. In this system, we applied the Tan and Triggs and retina modeling enhancement techniques, which are well suited for VLC and GOM, respectively. We evaluated our system on the standard FERET probe data sets and on extended YaleB database. The obtained results exhibited better face recognition rates in a shorter execution time compared to the GOM technique.

Highlights

Because of the increase and complexity of criminal behavior in modern societies, robust and efficient authentication systems became vital
This paper proposes a new face recognition system based on combining two feature extraction techniques: the Vander Lugt correlator (VLC) and Gabor ordinal measures (GOM)
From the last four tests, in which we combined the two feature extraction techniques VLC and GOM, we deduce that test 7 gives a better recognition rate when using, respectively, Tan and Triggs and retina modeling for image enhancement

Summary

Introduction

Because of the increase and complexity of criminal behavior in modern societies, robust and efficient authentication systems became vital. ), which can be either forgotten or stolen, biometric authentication systems offer a better solution for a wide range of applications like access control, criminal identification, etc. Different modalities are used in biometric systems such as iris, fingerprint, voice, and face recognition. The latter is widely used for many factors. Such a system is able to recognize people without their interaction. This makes the task more difficult due to some challenging factors such as pose variation, luminosity, facial expression in addition to the aging and the time-precision compromise. A face recognition system rests on four main steps: face detection, preprocessing, feature extraction, and classification

Methods

Results

Conclusion