Ecole d'ingénieur et centre de recherche en Sciences du numérique

3D face recognition: A robust multi-matcher approach to data degradations

Ben Amor, Boulbaba; Drira, Hassen; Daoudi, Mohamed; Ardabilian, Mohsen; Ben Soltana, Wael; Lemaire, Pierre; Chen, Liming; Erdogmus, Nesli; Dugelay, Jean-Luc; Colineau, Joseph

ICB 2012, 5th IAPR International Conference on Biometrics, 29 March-1 April 2012, New Delhi, India

Over the past decades, 3D face has emerged as a solution to face recognition due to its reputed invariance to lighting conditions and pose. While proposed approaches have proven their efficiency over renowned databases as FRGC, less effort was spent on studying the robustness of algorithms to quality degradations. In this paper, we present a study of the robustness of four state of the art algorithms and a multi-matcher framework to face model degradations such as Gaussian noise, decimation, and holes. The four state of the art algorithms were chosen for their different and complementary properties and exemplify the major classes of 3D face recognition solutions. As they displayed different behavior under data degradations, we further designed a fusion framework to best take into account their complementary properties. The proposed multi-matcher scheme is based on an offline and an online weight learning process. Experiments were conducted on a subset of the FRGC database, on which we generated degradations. Results demonstrate the competitive robustness of the proposed approach.

Document Doi Hal Bibtex

Titre:3D face recognition: A robust multi-matcher approach to data degradations
Type:Conférence
Langue:English
Ville:New Delhi
Pays:INDE
Date:
Département:Sécurité numérique
Eurecom ref:3589
Copyright: © 2012 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Bibtex: @inproceedings{EURECOM+3589, doi = {http://dx.doi.org/10.1109/ICB.2012.6199766}, year = {2012}, title = {3{D} face recognition: {A} robust multi-matcher approach to data degradations}, author = {{B}en {A}mor, {B}oulbaba and {D}rira, {H}assen and {D}aoudi, {M}ohamed and {A}rdabilian, {M}ohsen and {B}en {S}oltana, {W}ael and {L}emaire, {P}ierre and {C}hen, {L}iming and {E}rdogmus, {N}esli and {D}ugelay, {J}ean-{L}uc and {C}olineau, {J}oseph}, booktitle = {{ICB} 2012, 5th {IAPR} {I}nternational {C}onference on {B}iometrics, 29 {M}arch-1 {A}pril 2012, {N}ew {D}elhi, {I}ndia}, address = {{N}ew {D}elhi, {INDE}}, month = {03}, url = {http://www.eurecom.fr/publication/3589} }
Voir aussi: