Ocular Recognition Using Deep Features for Identity Authentication

Detalhes bibliográficos
Autor(a) principal: Vizoni, Marcelo V. [UNESP]
Data de Publicação: 2020
Outros Autores: Marana, Aparecido N. [UNESP]
Tipo de documento: Artigo de conferência
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.1109/IWSSIP48289.2020.9145418
http://hdl.handle.net/11449/199229
Resumo: Recently, ocular biometrics has been gaining importance in Biometrics due to the poor performance obtained in some cases by biometric systems based on characteristics of the whole face. This paper presents a new method for person authentication based on ocular deep features, which are extracted from the ocular region of the face by using a very deep CNN (Convolutional Neural Network). Another interesting aspect of our method is that, instead of using directly the deep features as input for the authentication system, it uses the difference between the probe and gallery deep features. So, our method adopts a pairwise strategy. A binary support vector machine is trained to determine whether a given difference vector is genuine or impostor. The proposed new method based on such pairwise strategy was evaluated using the ocular left set of the UBIPr dataset and five pre-trained CNN architectures. When using the pre-trained VGG-Face the proposed method obtained a state-of-the-art result (3.18% of Equal Error Rate).
id UNSP_036a06b2a31f21801e8886ee85ee4c86
oai_identifier_str oai:repositorio.unesp.br:11449/199229
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Ocular Recognition Using Deep Features for Identity Authenticationconvolutional neural networksdeep learningocular biometricsperson authenticationRecently, ocular biometrics has been gaining importance in Biometrics due to the poor performance obtained in some cases by biometric systems based on characteristics of the whole face. This paper presents a new method for person authentication based on ocular deep features, which are extracted from the ocular region of the face by using a very deep CNN (Convolutional Neural Network). Another interesting aspect of our method is that, instead of using directly the deep features as input for the authentication system, it uses the difference between the probe and gallery deep features. So, our method adopts a pairwise strategy. A binary support vector machine is trained to determine whether a given difference vector is genuine or impostor. The proposed new method based on such pairwise strategy was evaluated using the ocular left set of the UBIPr dataset and five pre-trained CNN architectures. When using the pre-trained VGG-Face the proposed method obtained a state-of-the-art result (3.18% of Equal Error Rate).São Paulo State University (UNESP)São Paulo State University (UNESP)Universidade Estadual Paulista (Unesp)Vizoni, Marcelo V. [UNESP]Marana, Aparecido N. [UNESP]2020-12-12T01:34:15Z2020-12-12T01:34:15Z2020-07-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject155-160http://dx.doi.org/10.1109/IWSSIP48289.2020.9145418International Conference on Systems, Signals, and Image Processing, v. 2020-July, p. 155-160.2157-87022157-8672http://hdl.handle.net/11449/19922910.1109/IWSSIP48289.2020.91454182-s2.0-85089143654Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengInternational Conference on Systems, Signals, and Image Processinginfo:eu-repo/semantics/openAccess2021-10-23T05:02:14Zoai:repositorio.unesp.br:11449/199229Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T19:14:43.096944Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Ocular Recognition Using Deep Features for Identity Authentication
title Ocular Recognition Using Deep Features for Identity Authentication
spellingShingle Ocular Recognition Using Deep Features for Identity Authentication
Vizoni, Marcelo V. [UNESP]
convolutional neural networks
deep learning
ocular biometrics
person authentication
title_short Ocular Recognition Using Deep Features for Identity Authentication
title_full Ocular Recognition Using Deep Features for Identity Authentication
title_fullStr Ocular Recognition Using Deep Features for Identity Authentication
title_full_unstemmed Ocular Recognition Using Deep Features for Identity Authentication
title_sort Ocular Recognition Using Deep Features for Identity Authentication
author Vizoni, Marcelo V. [UNESP]
author_facet Vizoni, Marcelo V. [UNESP]
Marana, Aparecido N. [UNESP]
author_role author
author2 Marana, Aparecido N. [UNESP]
author2_role author
dc.contributor.none.fl_str_mv Universidade Estadual Paulista (Unesp)
dc.contributor.author.fl_str_mv Vizoni, Marcelo V. [UNESP]
Marana, Aparecido N. [UNESP]
dc.subject.por.fl_str_mv convolutional neural networks
deep learning
ocular biometrics
person authentication
topic convolutional neural networks
deep learning
ocular biometrics
person authentication
description Recently, ocular biometrics has been gaining importance in Biometrics due to the poor performance obtained in some cases by biometric systems based on characteristics of the whole face. This paper presents a new method for person authentication based on ocular deep features, which are extracted from the ocular region of the face by using a very deep CNN (Convolutional Neural Network). Another interesting aspect of our method is that, instead of using directly the deep features as input for the authentication system, it uses the difference between the probe and gallery deep features. So, our method adopts a pairwise strategy. A binary support vector machine is trained to determine whether a given difference vector is genuine or impostor. The proposed new method based on such pairwise strategy was evaluated using the ocular left set of the UBIPr dataset and five pre-trained CNN architectures. When using the pre-trained VGG-Face the proposed method obtained a state-of-the-art result (3.18% of Equal Error Rate).
publishDate 2020
dc.date.none.fl_str_mv 2020-12-12T01:34:15Z
2020-12-12T01:34:15Z
2020-07-01
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/conferenceObject
format conferenceObject
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://dx.doi.org/10.1109/IWSSIP48289.2020.9145418
International Conference on Systems, Signals, and Image Processing, v. 2020-July, p. 155-160.
2157-8702
2157-8672
http://hdl.handle.net/11449/199229
10.1109/IWSSIP48289.2020.9145418
2-s2.0-85089143654
url http://dx.doi.org/10.1109/IWSSIP48289.2020.9145418
http://hdl.handle.net/11449/199229
identifier_str_mv International Conference on Systems, Signals, and Image Processing, v. 2020-July, p. 155-160.
2157-8702
2157-8672
10.1109/IWSSIP48289.2020.9145418
2-s2.0-85089143654
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv International Conference on Systems, Signals, and Image Processing
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 155-160
dc.source.none.fl_str_mv Scopus
reponame:Repositório Institucional da UNESP
instname:Universidade Estadual Paulista (UNESP)
instacron:UNESP
instname_str Universidade Estadual Paulista (UNESP)
instacron_str UNESP
institution UNESP
reponame_str Repositório Institucional da UNESP
collection Repositório Institucional da UNESP
repository.name.fl_str_mv Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)
repository.mail.fl_str_mv
_version_ 1808129040400252928