Deep periocular representation aiming video surveillance.
Autor(a) principal: | |
---|---|
Data de Publicação: | 2017 |
Outros Autores: | , , |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFOP |
Texto Completo: | http://www.repositorio.ufop.br/handle/123456789/10370 https://www.sciencedirect.com/science/article/pii/S0167865517304476 |
Resumo: | Usually, in the deep learning community, it is claimed that generalized representations that yielding out- standing performance / effectiveness require a huge amount of data for learning, which directly affect biometric applications. However, recent works combining transfer learning from other domains have sur- mounted such data application constraints designing interesting and promising deep learning approaches in diverse scenarios where data is not so abundant. In this direction, a biometric system for the peri- ocular region based on deep learning approach is designed and applied on two non-cooperative ocular databases. Impressive representation discrimination is achieved with transfer learning from the facial do- main (a deep convolutional network, called VGG) and fine tuning in the specific periocular region domain. With this design, our proposal surmounts previous state-of-the-art results on NICE (mean decidability of 3.47 against 2.57) and MobBio (equal error rate of 5.42% against 8.73%) competition databases. |
id |
UFOP_1fd8b2f538f102a86cdafcd527bce6bd |
---|---|
oai_identifier_str |
oai:localhost:123456789/10370 |
network_acronym_str |
UFOP |
network_name_str |
Repositório Institucional da UFOP |
repository_id_str |
3233 |
spelling |
Moreira, Gladston Juliano PratesLuz, Eduardo José da SilvaJunior, Luiz Antonio ZanlorensiGomes, David Menotti2018-10-16T12:55:19Z2018-10-16T12:55:19Z2017MOREIRA, G. J. P. et al. Deep periocular representation aiming video surveillance. Pattern Recognition Letters, v. 114, p. 2-12, 2018. Disponível em: <https://www.sciencedirect.com/science/article/pii/S0167865517304476>. Acesso em: 16 jun. 2018. 01678655http://www.repositorio.ufop.br/handle/123456789/10370https://www.sciencedirect.com/science/article/pii/S0167865517304476Usually, in the deep learning community, it is claimed that generalized representations that yielding out- standing performance / effectiveness require a huge amount of data for learning, which directly affect biometric applications. However, recent works combining transfer learning from other domains have sur- mounted such data application constraints designing interesting and promising deep learning approaches in diverse scenarios where data is not so abundant. In this direction, a biometric system for the peri- ocular region based on deep learning approach is designed and applied on two non-cooperative ocular databases. Impressive representation discrimination is achieved with transfer learning from the facial do- main (a deep convolutional network, called VGG) and fine tuning in the specific periocular region domain. With this design, our proposal surmounts previous state-of-the-art results on NICE (mean decidability of 3.47 against 2.57) and MobBio (equal error rate of 5.42% against 8.73%) competition databases.Deep learningTransfer learningVGG Periocular regionVideo surveillanceDeep periocular representation aiming video surveillance.info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisinfo:eu-repo/semantics/openAccessengreponame:Repositório Institucional da UFOPinstname:Universidade Federal de Ouro Preto (UFOP)instacron:UFOPLICENSElicense.txtlicense.txttext/plain; charset=utf-8924http://www.repositorio.ufop.br/bitstream/123456789/10370/2/license.txt62604f8d955274beb56c80ce1ee5dcaeMD52ORIGINALARTIGO_DeepPeriocularRepresentation.pdfARTIGO_DeepPeriocularRepresentation.pdfapplication/pdf2498981http://www.repositorio.ufop.br/bitstream/123456789/10370/1/ARTIGO_DeepPeriocularRepresentation.pdf4587ecd5ba4104393eaed41cc634d274MD51123456789/103702019-03-18 13:25:26.084oai:localhost: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ório InstitucionalPUBhttp://www.repositorio.ufop.br/oai/requestrepositorio@ufop.edu.bropendoar:32332019-03-18T17:25:26Repositório Institucional da UFOP - Universidade Federal de Ouro Preto (UFOP)false |
dc.title.pt_BR.fl_str_mv |
Deep periocular representation aiming video surveillance. |
title |
Deep periocular representation aiming video surveillance. |
spellingShingle |
Deep periocular representation aiming video surveillance. Moreira, Gladston Juliano Prates Deep learning Transfer learning VGG Periocular region Video surveillance |
title_short |
Deep periocular representation aiming video surveillance. |
title_full |
Deep periocular representation aiming video surveillance. |
title_fullStr |
Deep periocular representation aiming video surveillance. |
title_full_unstemmed |
Deep periocular representation aiming video surveillance. |
title_sort |
Deep periocular representation aiming video surveillance. |
author |
Moreira, Gladston Juliano Prates |
author_facet |
Moreira, Gladston Juliano Prates Luz, Eduardo José da Silva Junior, Luiz Antonio Zanlorensi Gomes, David Menotti |
author_role |
author |
author2 |
Luz, Eduardo José da Silva Junior, Luiz Antonio Zanlorensi Gomes, David Menotti |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Moreira, Gladston Juliano Prates Luz, Eduardo José da Silva Junior, Luiz Antonio Zanlorensi Gomes, David Menotti |
dc.subject.por.fl_str_mv |
Deep learning Transfer learning VGG Periocular region Video surveillance |
topic |
Deep learning Transfer learning VGG Periocular region Video surveillance |
description |
Usually, in the deep learning community, it is claimed that generalized representations that yielding out- standing performance / effectiveness require a huge amount of data for learning, which directly affect biometric applications. However, recent works combining transfer learning from other domains have sur- mounted such data application constraints designing interesting and promising deep learning approaches in diverse scenarios where data is not so abundant. In this direction, a biometric system for the peri- ocular region based on deep learning approach is designed and applied on two non-cooperative ocular databases. Impressive representation discrimination is achieved with transfer learning from the facial do- main (a deep convolutional network, called VGG) and fine tuning in the specific periocular region domain. With this design, our proposal surmounts previous state-of-the-art results on NICE (mean decidability of 3.47 against 2.57) and MobBio (equal error rate of 5.42% against 8.73%) competition databases. |
publishDate |
2017 |
dc.date.issued.fl_str_mv |
2017 |
dc.date.accessioned.fl_str_mv |
2018-10-16T12:55:19Z |
dc.date.available.fl_str_mv |
2018-10-16T12:55:19Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.citation.fl_str_mv |
MOREIRA, G. J. P. et al. Deep periocular representation aiming video surveillance. Pattern Recognition Letters, v. 114, p. 2-12, 2018. Disponível em: <https://www.sciencedirect.com/science/article/pii/S0167865517304476>. Acesso em: 16 jun. 2018. |
dc.identifier.uri.fl_str_mv |
http://www.repositorio.ufop.br/handle/123456789/10370 |
dc.identifier.issn.none.fl_str_mv |
01678655 |
dc.identifier.uri2.pt_BR.fl_str_mv |
https://www.sciencedirect.com/science/article/pii/S0167865517304476 |
identifier_str_mv |
MOREIRA, G. J. P. et al. Deep periocular representation aiming video surveillance. Pattern Recognition Letters, v. 114, p. 2-12, 2018. Disponível em: <https://www.sciencedirect.com/science/article/pii/S0167865517304476>. Acesso em: 16 jun. 2018. 01678655 |
url |
http://www.repositorio.ufop.br/handle/123456789/10370 https://www.sciencedirect.com/science/article/pii/S0167865517304476 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFOP instname:Universidade Federal de Ouro Preto (UFOP) instacron:UFOP |
instname_str |
Universidade Federal de Ouro Preto (UFOP) |
instacron_str |
UFOP |
institution |
UFOP |
reponame_str |
Repositório Institucional da UFOP |
collection |
Repositório Institucional da UFOP |
bitstream.url.fl_str_mv |
http://www.repositorio.ufop.br/bitstream/123456789/10370/2/license.txt http://www.repositorio.ufop.br/bitstream/123456789/10370/1/ARTIGO_DeepPeriocularRepresentation.pdf |
bitstream.checksum.fl_str_mv |
62604f8d955274beb56c80ce1ee5dcae 4587ecd5ba4104393eaed41cc634d274 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFOP - Universidade Federal de Ouro Preto (UFOP) |
repository.mail.fl_str_mv |
repositorio@ufop.edu.br |
_version_ |
1797950112557694976 |