Analysis of a GPU implementation of Viola-Jones' Algorithm for Features Selection

Autores
Lescano, Germán Ezequiel; Santana Mansilla, Pablo Fernando; Costaguta, Rosanna Nieves
Año de publicación
2017
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Faces and facial expressions recognition is an interesting topic for researchers in machine vision. Viola-Jones algorithm is the most spread algorithm for this task. Building a classification model for face recognition can take many years if the implementation of its training phase is not optimized. In this study, we analyze different implementations for the training phase. The aim was to reduce the time needed during training phase when using one computer with a cheap graphical processing unit (GPU). The execution times were analyzed and compared with previous studies. Results showed that combining C language, CUDA, etc., it is possible to reach acceptable times for training phase. Further research may involve the measurement of the performance of our approach computers with better GPU capacity and exploring a multi-GPU approach.
Fil: Lescano, Germán Ezequiel. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional de Santiago del Estero. Facultad de Ciencias Exactas y Tecnologías; Argentina
Fil: Santana Mansilla, Pablo Fernando. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional de Santiago del Estero. Facultad de Ciencias Exactas y Tecnologías; Argentina
Fil: Costaguta, Rosanna Nieves. Universidad Nacional de Santiago del Estero. Facultad de Ciencias Exactas y Tecnologías; Argentina
Materia
ADABOOST
VIOLA-JONES ALGORITHM
FEATURE SELECTION
CUDA
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/74112
Acceder
id CONICETDig_b7d58992c8cfdb86d2ed6b2864bc7659
oai_identifier_str oai:ri.conicet.gov.ar:11336/74112
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Analysis of a GPU implementation of Viola-Jones' Algorithm for Features SelectionLescano, Germán EzequielSantana Mansilla, Pablo FernandoCostaguta, Rosanna NievesADABOOSTVIOLA-JONES ALGORITHMFEATURE SELECTIONCUDAhttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1https://purl.org/becyt/ford/1.1https://purl.org/becyt/ford/1Faces and facial expressions recognition is an interesting topic for researchers in machine vision. Viola-Jones algorithm is the most spread algorithm for this task. Building a classification model for face recognition can take many years if the implementation of its training phase is not optimized. In this study, we analyze different implementations for the training phase. The aim was to reduce the time needed during training phase when using one computer with a cheap graphical processing unit (GPU). The execution times were analyzed and compared with previous studies. Results showed that combining C language, CUDA, etc., it is possible to reach acceptable times for training phase. Further research may involve the measurement of the performance of our approach computers with better GPU capacity and exploring a multi-GPU approach.Fil: Lescano, Germán Ezequiel. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional de Santiago del Estero. Facultad de Ciencias Exactas y Tecnologías; ArgentinaFil: Santana Mansilla, Pablo Fernando. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional de Santiago del Estero. Facultad de Ciencias Exactas y Tecnologías; ArgentinaFil: Costaguta, Rosanna Nieves. Universidad Nacional de Santiago del Estero. Facultad de Ciencias Exactas y Tecnologías; ArgentinaUniversidad Nacional de La Plata. Facultad de Informática2017-12info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/74112Lescano, Germán Ezequiel; Santana Mansilla, Pablo Fernando; Costaguta, Rosanna Nieves; Analysis of a GPU implementation of Viola-Jones' Algorithm for Features Selection; Universidad Nacional de La Plata. Facultad de Informática; Journal of Computer Science & Technology; 17; 1; 12-2017; 68-731666-60381666-6046CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/http://journal.info.unlp.edu.ar/JCST/article/view/449info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-03T09:44:34Zoai:ri.conicet.gov.ar:11336/74112instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-03 09:44:34.776CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Analysis of a GPU implementation of Viola-Jones' Algorithm for Features Selection
title Analysis of a GPU implementation of Viola-Jones' Algorithm for Features Selection
spellingShingle Analysis of a GPU implementation of Viola-Jones' Algorithm for Features Selection
Lescano, Germán Ezequiel
ADABOOST
VIOLA-JONES ALGORITHM
FEATURE SELECTION
CUDA
title_short Analysis of a GPU implementation of Viola-Jones' Algorithm for Features Selection
title_full Analysis of a GPU implementation of Viola-Jones' Algorithm for Features Selection
title_fullStr Analysis of a GPU implementation of Viola-Jones' Algorithm for Features Selection
title_full_unstemmed Analysis of a GPU implementation of Viola-Jones' Algorithm for Features Selection
title_sort Analysis of a GPU implementation of Viola-Jones' Algorithm for Features Selection
dc.creator.none.fl_str_mv Lescano, Germán Ezequiel
Santana Mansilla, Pablo Fernando
Costaguta, Rosanna Nieves
author Lescano, Germán Ezequiel
author_facet Lescano, Germán Ezequiel
Santana Mansilla, Pablo Fernando
Costaguta, Rosanna Nieves
author_role author
author2 Santana Mansilla, Pablo Fernando
Costaguta, Rosanna Nieves
author2_role author
author
dc.subject.none.fl_str_mv ADABOOST
VIOLA-JONES ALGORITHM
FEATURE SELECTION
CUDA
topic ADABOOST
VIOLA-JONES ALGORITHM
FEATURE SELECTION
CUDA
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
https://purl.org/becyt/ford/1.1
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv Faces and facial expressions recognition is an interesting topic for researchers in machine vision. Viola-Jones algorithm is the most spread algorithm for this task. Building a classification model for face recognition can take many years if the implementation of its training phase is not optimized. In this study, we analyze different implementations for the training phase. The aim was to reduce the time needed during training phase when using one computer with a cheap graphical processing unit (GPU). The execution times were analyzed and compared with previous studies. Results showed that combining C language, CUDA, etc., it is possible to reach acceptable times for training phase. Further research may involve the measurement of the performance of our approach computers with better GPU capacity and exploring a multi-GPU approach.
Fil: Lescano, Germán Ezequiel. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional de Santiago del Estero. Facultad de Ciencias Exactas y Tecnologías; Argentina
Fil: Santana Mansilla, Pablo Fernando. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional de Santiago del Estero. Facultad de Ciencias Exactas y Tecnologías; Argentina
Fil: Costaguta, Rosanna Nieves. Universidad Nacional de Santiago del Estero. Facultad de Ciencias Exactas y Tecnologías; Argentina
description Faces and facial expressions recognition is an interesting topic for researchers in machine vision. Viola-Jones algorithm is the most spread algorithm for this task. Building a classification model for face recognition can take many years if the implementation of its training phase is not optimized. In this study, we analyze different implementations for the training phase. The aim was to reduce the time needed during training phase when using one computer with a cheap graphical processing unit (GPU). The execution times were analyzed and compared with previous studies. Results showed that combining C language, CUDA, etc., it is possible to reach acceptable times for training phase. Further research may involve the measurement of the performance of our approach computers with better GPU capacity and exploring a multi-GPU approach.
publishDate 2017
dc.date.none.fl_str_mv 2017-12
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/74112
Lescano, Germán Ezequiel; Santana Mansilla, Pablo Fernando; Costaguta, Rosanna Nieves; Analysis of a GPU implementation of Viola-Jones' Algorithm for Features Selection; Universidad Nacional de La Plata. Facultad de Informática; Journal of Computer Science & Technology; 17; 1; 12-2017; 68-73
1666-6038
1666-6046
CONICET Digital
CONICET
url http://hdl.handle.net/11336/74112
identifier_str_mv Lescano, Germán Ezequiel; Santana Mansilla, Pablo Fernando; Costaguta, Rosanna Nieves; Analysis of a GPU implementation of Viola-Jones' Algorithm for Features Selection; Universidad Nacional de La Plata. Facultad de Informática; Journal of Computer Science & Technology; 17; 1; 12-2017; 68-73
1666-6038
1666-6046
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/http://journal.info.unlp.edu.ar/JCST/article/view/449
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Universidad Nacional de La Plata. Facultad de Informática
publisher.none.fl_str_mv Universidad Nacional de La Plata. Facultad de Informática
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1842268675644588032
score 13.13397

Publicaciones similares