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

Advanced face presentation attack detection on light field images

Chiesa, Valeria; Dugelay, Jean-Luc

BIOSIG 2018, 17th International Conference of the Biometrics Special Interest Group, 26-29 September 2018, Darmstadt, Germany

In the last years several works have been focused on the impact of new sensors on face recognition. A particular interest has been addressed to technologies able to detect the depth of the scene as light field cameras. Together with person identification algorithms, new anti-spoofing methods customized for specific devices have to be investigated. In this paper, a new algorithm for presentation attack detection on light field face database is proposed. While distance between subject and camera is not a relevant information for standard 2D spoofing attacks, it could be important when using 3D cameras. We prove through three experiments that the proposed method based on depth map elaboration outperforms the existent algorithms in presentation attack detection on light field images.

Document Doi Bibtex

Titre:Advanced face presentation attack detection on light field images
Mots Clés:Light field, Presentation attack detection, Anti-spoofing, Depth map
Département:Sécurité numérique
Eurecom ref:5701
Copyright: © 2018 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+5701, doi = {}, year = {2018}, title = {{A}dvanced face presentation attack detection on light field images}, author = {{C}hiesa, {V}aleria and {D}ugelay, {J}ean-{L}uc}, booktitle = {{BIOSIG} 2018, 17th {I}nternational {C}onference of the {B}iometrics {S}pecial {I}nterest {G}roup, 26-29 {S}eptember 2018, {D}armstadt, {G}ermany}, address = {{D}armstadt, {ALLEMAGNE}}, month = {09}, url = {} }
Voir aussi: