Deep Learning from 3DLBP Descriptors for Depth Image Based Face Recognition
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Outros Autores: | , , , |
Tipo de documento: | Artigo de conferência |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1109/ICB45273.2019.8987432 http://hdl.handle.net/11449/198598 |
Resumo: | In this paper, we propose a new framework for face recognition from depth images, which is both effective and efficient. It consists of two main stages: First, a handcrafted low-level feature extractor is applied to the raw depth data of the face, thus extracting the corresponding descriptor images (DIs); Then, a not-so-deep (shallow) convolutional neural network (SCNN) has been designed that learns from the DIs. This architecture showed two main advantages over the direct application of deep-CNN (DCNN) to the depth images of the face: On the one hand, the DIs are capable of enriching the raw depth data, emphasizing relevant traits of the face, while reducing their acquisition noise. This resulted decisive in improving the learning capability of the network; On the other, the DIs capture low-level features of the face, thus playing the role for the SCNN as the first layers do in a DCNN architecture. In this way, the SCNN we have designed has much less layers and can be trained more easily and faster. Extensive experiments on low- and high-resolution depth face datasets confirmed us the above advantages, showing results that are comparable or superior to the state-of-the-art, using by far less training data, time, and memory occupancy of the network. |
id |
UNSP_11f0512c67d8ae2adafc9f3906250448 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/198598 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Deep Learning from 3DLBP Descriptors for Depth Image Based Face RecognitionIn this paper, we propose a new framework for face recognition from depth images, which is both effective and efficient. It consists of two main stages: First, a handcrafted low-level feature extractor is applied to the raw depth data of the face, thus extracting the corresponding descriptor images (DIs); Then, a not-so-deep (shallow) convolutional neural network (SCNN) has been designed that learns from the DIs. This architecture showed two main advantages over the direct application of deep-CNN (DCNN) to the depth images of the face: On the one hand, the DIs are capable of enriching the raw depth data, emphasizing relevant traits of the face, while reducing their acquisition noise. This resulted decisive in improving the learning capability of the network; On the other, the DIs capture low-level features of the face, thus playing the role for the SCNN as the first layers do in a DCNN architecture. In this way, the SCNN we have designed has much less layers and can be trained more easily and faster. Extensive experiments on low- and high-resolution depth face datasets confirmed us the above advantages, showing results that are comparable or superior to the state-of-the-art, using by far less training data, time, and memory occupancy of the network.São Carlos Federal University - UFSCARUNESP - São Paulo State UniversityUniversity of Florence Media Integration and Communication CenterUNESP - São Paulo State UniversityUniversidade Federal de São Carlos (UFSCar)Universidade Estadual Paulista (Unesp)Media Integration and Communication CenterCardia Neto, Joao BaptistaNilceu Marana, Aparecido [UNESP]Ferrari, ClaudioBerretti, StefanoDel Bimbo, Alberto2020-12-12T01:17:11Z2020-12-12T01:17:11Z2019-06-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObjecthttp://dx.doi.org/10.1109/ICB45273.2019.89874322019 International Conference on Biometrics, ICB 2019.http://hdl.handle.net/11449/19859810.1109/ICB45273.2019.89874322-s2.0-85081063486Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPeng2019 International Conference on Biometrics, ICB 2019info:eu-repo/semantics/openAccess2021-10-22T17:19:45Zoai:repositorio.unesp.br:11449/198598Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-06T00:05:55.303330Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Deep Learning from 3DLBP Descriptors for Depth Image Based Face Recognition |
title |
Deep Learning from 3DLBP Descriptors for Depth Image Based Face Recognition |
spellingShingle |
Deep Learning from 3DLBP Descriptors for Depth Image Based Face Recognition Cardia Neto, Joao Baptista |
title_short |
Deep Learning from 3DLBP Descriptors for Depth Image Based Face Recognition |
title_full |
Deep Learning from 3DLBP Descriptors for Depth Image Based Face Recognition |
title_fullStr |
Deep Learning from 3DLBP Descriptors for Depth Image Based Face Recognition |
title_full_unstemmed |
Deep Learning from 3DLBP Descriptors for Depth Image Based Face Recognition |
title_sort |
Deep Learning from 3DLBP Descriptors for Depth Image Based Face Recognition |
author |
Cardia Neto, Joao Baptista |
author_facet |
Cardia Neto, Joao Baptista Nilceu Marana, Aparecido [UNESP] Ferrari, Claudio Berretti, Stefano Del Bimbo, Alberto |
author_role |
author |
author2 |
Nilceu Marana, Aparecido [UNESP] Ferrari, Claudio Berretti, Stefano Del Bimbo, Alberto |
author2_role |
author author author author |
dc.contributor.none.fl_str_mv |
Universidade Federal de São Carlos (UFSCar) Universidade Estadual Paulista (Unesp) Media Integration and Communication Center |
dc.contributor.author.fl_str_mv |
Cardia Neto, Joao Baptista Nilceu Marana, Aparecido [UNESP] Ferrari, Claudio Berretti, Stefano Del Bimbo, Alberto |
description |
In this paper, we propose a new framework for face recognition from depth images, which is both effective and efficient. It consists of two main stages: First, a handcrafted low-level feature extractor is applied to the raw depth data of the face, thus extracting the corresponding descriptor images (DIs); Then, a not-so-deep (shallow) convolutional neural network (SCNN) has been designed that learns from the DIs. This architecture showed two main advantages over the direct application of deep-CNN (DCNN) to the depth images of the face: On the one hand, the DIs are capable of enriching the raw depth data, emphasizing relevant traits of the face, while reducing their acquisition noise. This resulted decisive in improving the learning capability of the network; On the other, the DIs capture low-level features of the face, thus playing the role for the SCNN as the first layers do in a DCNN architecture. In this way, the SCNN we have designed has much less layers and can be trained more easily and faster. Extensive experiments on low- and high-resolution depth face datasets confirmed us the above advantages, showing results that are comparable or superior to the state-of-the-art, using by far less training data, time, and memory occupancy of the network. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-06-01 2020-12-12T01:17:11Z 2020-12-12T01:17:11Z |
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/ICB45273.2019.8987432 2019 International Conference on Biometrics, ICB 2019. http://hdl.handle.net/11449/198598 10.1109/ICB45273.2019.8987432 2-s2.0-85081063486 |
url |
http://dx.doi.org/10.1109/ICB45273.2019.8987432 http://hdl.handle.net/11449/198598 |
identifier_str_mv |
2019 International Conference on Biometrics, ICB 2019. 10.1109/ICB45273.2019.8987432 2-s2.0-85081063486 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
2019 International Conference on Biometrics, ICB 2019 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
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_ |
1808129582510899200 |