Convolutional Neural Network Approach for Multispectral Facial Presentation Attack Detection in Automated Border Control Systems

[EN] Automated border control systems are the first critical infrastructure point when crossing a border country. Crossing border lines for unauthorized passengers is a high security risk to any country. This paper presents a multispectral analysis of presentation attack detection for facial biometr...

Descripción completa

Detalles Bibliográficos
Autores: Gómez-Ayllón, Beatriz, Ortega-DelCampo, David, Tsitiridis, Aristeidis, Palacios-Alonso, Daniel, Sánchez Sánchez, María Araceli, Conde, Cristina, Cabello, Enrique
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2020
País:España
Institución:Universidad de Salamanca (USAL)
Repositorio:GREDOS. Repositorio Institucional de la Universidad de Salamanca
OAI Identifier:oai:gredos.usal.es:10366/145498
Acceso en línea:http://hdl.handle.net/10366/145498
Access Level:acceso abierto
Palabra clave:Biometrics
Presentation attack detection
Anti-spoofing
Automatic border crossing systems
Convolutional neural network
Bio-inspired systems
1203 Ciencia de los ordenadores
1203.17 Informática
id ES_ffa7e8a44ae67b2dfe2c19bb6a6a33fe
oai_identifier_str oai:gredos.usal.es:10366/145498
network_acronym_str ES
network_name_str España
repository_id_str
spelling Convolutional Neural Network Approach for Multispectral Facial Presentation Attack Detection in Automated Border Control SystemsGómez-Ayllón, BeatrizOrtega-DelCampo, DavidTsitiridis, AristeidisPalacios-Alonso, DanielSánchez Sánchez, María AraceliConde, CristinaCabello, EnriqueBiometricsPresentation attack detectionAnti-spoofingAutomatic border crossing systemsConvolutional neural networkBio-inspired systems1203 Ciencia de los ordenadores1203.17 Informática[EN] Automated border control systems are the first critical infrastructure point when crossing a border country. Crossing border lines for unauthorized passengers is a high security risk to any country. This paper presents a multispectral analysis of presentation attack detection for facial biometrics using the learned features from a convolutional neural network. Three sensors are considered to design and develop a new database that is composed of visible (VIS), near-infrared (NIR), and thermal images. Most studies are based on laboratory or ideal conditions-controlled environments. However, in a real scenario, a subject’s situation is completely modified due to diverse physiological conditions, such as stress, temperature changes, sweating, and increased blood pressure. For this reason, the added value of this study is that this database was acquired in situ. The attacks considered were printed, masked, and displayed images. In addition, five classifiers were used to detect the presentation attack. Note that thermal sensors provide better performance than other solutions. The results present better outputs when all sensors are used together, regardless of whether classifier or feature-level fusion is considered. Finally, classifiers such as KNN or SVM show high performance and low computational level.Entropy202120212020info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttp://hdl.handle.net/10366/145498reponame:GREDOS. Repositorio Institucional de la Universidad de Salamancainstname:Universidad de Salamanca (USAL)InglésAttribution-NonCommercial-NoDerivatives 4.0 Internacionalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:gredos.usal.es:10366/1454982026-06-07T06:28:51Z
dc.title.none.fl_str_mv Convolutional Neural Network Approach for Multispectral Facial Presentation Attack Detection in Automated Border Control Systems
title Convolutional Neural Network Approach for Multispectral Facial Presentation Attack Detection in Automated Border Control Systems
spellingShingle Convolutional Neural Network Approach for Multispectral Facial Presentation Attack Detection in Automated Border Control Systems
Gómez-Ayllón, Beatriz
Biometrics
Presentation attack detection
Anti-spoofing
Automatic border crossing systems
Convolutional neural network
Bio-inspired systems
1203 Ciencia de los ordenadores
1203.17 Informática
title_short Convolutional Neural Network Approach for Multispectral Facial Presentation Attack Detection in Automated Border Control Systems
title_full Convolutional Neural Network Approach for Multispectral Facial Presentation Attack Detection in Automated Border Control Systems
title_fullStr Convolutional Neural Network Approach for Multispectral Facial Presentation Attack Detection in Automated Border Control Systems
title_full_unstemmed Convolutional Neural Network Approach for Multispectral Facial Presentation Attack Detection in Automated Border Control Systems
title_sort Convolutional Neural Network Approach for Multispectral Facial Presentation Attack Detection in Automated Border Control Systems
dc.creator.none.fl_str_mv Gómez-Ayllón, Beatriz
Ortega-DelCampo, David
Tsitiridis, Aristeidis
Palacios-Alonso, Daniel
Sánchez Sánchez, María Araceli
Conde, Cristina
Cabello, Enrique
author Gómez-Ayllón, Beatriz
author_facet Gómez-Ayllón, Beatriz
Ortega-DelCampo, David
Tsitiridis, Aristeidis
Palacios-Alonso, Daniel
Sánchez Sánchez, María Araceli
Conde, Cristina
Cabello, Enrique
author_role author
author2 Ortega-DelCampo, David
Tsitiridis, Aristeidis
Palacios-Alonso, Daniel
Sánchez Sánchez, María Araceli
Conde, Cristina
Cabello, Enrique
author2_role author
author
author
author
author
author
dc.subject.none.fl_str_mv Biometrics
Presentation attack detection
Anti-spoofing
Automatic border crossing systems
Convolutional neural network
Bio-inspired systems
1203 Ciencia de los ordenadores
1203.17 Informática
topic Biometrics
Presentation attack detection
Anti-spoofing
Automatic border crossing systems
Convolutional neural network
Bio-inspired systems
1203 Ciencia de los ordenadores
1203.17 Informática
description [EN] Automated border control systems are the first critical infrastructure point when crossing a border country. Crossing border lines for unauthorized passengers is a high security risk to any country. This paper presents a multispectral analysis of presentation attack detection for facial biometrics using the learned features from a convolutional neural network. Three sensors are considered to design and develop a new database that is composed of visible (VIS), near-infrared (NIR), and thermal images. Most studies are based on laboratory or ideal conditions-controlled environments. However, in a real scenario, a subject’s situation is completely modified due to diverse physiological conditions, such as stress, temperature changes, sweating, and increased blood pressure. For this reason, the added value of this study is that this database was acquired in situ. The attacks considered were printed, masked, and displayed images. In addition, five classifiers were used to detect the presentation attack. Note that thermal sensors provide better performance than other solutions. The results present better outputs when all sensors are used together, regardless of whether classifier or feature-level fusion is considered. Finally, classifiers such as KNN or SVM show high performance and low computational level.
publishDate 2020
dc.date.none.fl_str_mv 2020
2021
2021
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10366/145498
url http://hdl.handle.net/10366/145498
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv Attribution-NonCommercial-NoDerivatives 4.0 Internacional
http://creativecommons.org/licenses/by-nc-nd/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Attribution-NonCommercial-NoDerivatives 4.0 Internacional
http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Entropy
publisher.none.fl_str_mv Entropy
dc.source.none.fl_str_mv reponame:GREDOS. Repositorio Institucional de la Universidad de Salamanca
instname:Universidad de Salamanca (USAL)
instname_str Universidad de Salamanca (USAL)
reponame_str GREDOS. Repositorio Institucional de la Universidad de Salamanca
collection GREDOS. Repositorio Institucional de la Universidad de Salamanca
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869425793866661888
score 15,300724

Similares en LA Referencia