Bio-inspired Face Authentication using Multiscale LBP

Ayoub Elghanaoui, Nefissa Khiari Hili, Christophe Montagne, Sylvie Lelandais

2013

Abstract

In this paper, we propose a new approach to recognize 2D faces. This approach is based on experiments performed in the field of cognitive science to understand how people recognize a face. To extract features, the image is first decomposed on a base of wavelets using four-level Difference Of Gaussians (DOGs) functions which are a good modeling of human visual system; then different Regions Of Interest (ROIs) are selected on each scale, related to the cognitive method we refer to. After that, Local Binary Patterns (LBP) histograms are computed on each block of the ROIs and concatenated to form the final feature vector. Matching is performed by means of a weighted distance. Weighting coefficients are chosen based on results of psychovisual experiments in which the task assigned to observers was to recognize people. Proposed approach was tested on IV² database and experimental results prove its efficiency when compared to classical face recognition algorithms.

Paper Citation

in Harvard Style

Elghanaoui A., Khiari Hili N., Montagne C. and Lelandais S. (2013). Bio-inspired Face Authentication using Multiscale LBP . In Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2013) ISBN 978-989-8565-36-5, pages 182-188. DOI: 10.5220/0004235601820188

in Bibtex Style

@conference{biosignals13,
author={Ayoub Elghanaoui and Nefissa Khiari Hili and Christophe Montagne and Sylvie Lelandais},
title={Bio-inspired Face Authentication using Multiscale LBP},
booktitle={Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2013)},
year={2013},
pages={182-188},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004235601820188},
isbn={978-989-8565-36-5},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2013)
TI - Bio-inspired Face Authentication using Multiscale LBP
SN - 978-989-8565-36-5
AU - Elghanaoui A.
AU - Khiari Hili N.
AU - Montagne C.
AU - Lelandais S.
PY - 2013
SP - 182
EP - 188
DO - 10.5220/0004235601820188