Evaluation of LBP and HOG descriptors for clothing attribute description

In this work an experimental study about the capability of the LBP, HOG descriptors and color for clothing attribute classification is presented. Two different variants of the LBP descriptor are considered, the original LBP and the uniform LBP. Two classifiers, Linear SVM and Random Forest, have been i...

Descripción completa

Detalles Bibliográficos
Autores: Lorenzo Navarro, José Javier, Castrillón-Santana, Modesto, Ramón Balmaseda, Enrique José, Freire, David
Tipo de recurso: capítulo de libro
Fecha de publicación:2014
País:España
Repositorio:accedaCRIS portal de investigación de la Universidad de las Palmas de Gran Canaria
OAI Identifier:oai:accedacris.ulpgc.es:10553/15753
Acceso en línea:http://hdl.handle.net/10553/15753
Access Level:acceso abierto
Palabra clave:120304 Inteligencia artificial
LBP
HOG
Clothing description
id ES_cf86a8b36f2d9c2985c8d6577f9a9bd7
oai_identifier_str oai:accedacris.ulpgc.es:10553/15753
network_acronym_str ES
network_name_str España
repository_id_str
spelling Evaluation of LBP and HOG descriptors for clothing attribute descriptionLorenzo Navarro, José JavierCastrillón-Santana, ModestoRamón Balmaseda, Enrique JoséFreire, David120304 Inteligencia artificialLBPHOGClothing descriptionIn this work an experimental study about the capability of the LBP, HOG descriptors and color for clothing attribute classification is presented. Two different variants of the LBP descriptor are considered, the original LBP and the uniform LBP. Two classifiers, Linear SVM and Random Forest, have been included in the comparison because they have been frequently used in clothing attributes classification. The experiments are carried out with a public available dataset, the clothing attribute dataset, that has 26 attributes in total. The obtained accuracies are over 75% in most cases, reaching 80% for the necktie or sleeve length attributes.6553130,325Q3Springer1504245380022333278500564947442003507830400024896953214542858710355069358WOS:Lorenzo-Navarro, JWOS:Castrillon, MWOS:Ramon, EWOS:Freire, D20162018201620182014Enerinfo:eu-repo/semantics/bookPartBook parthttp://hdl.handle.net/10553/15753Video Analytics for Audience Measurement. VAAM 2014. Lecture Notes in Computer Science, v. 8811 LNCS, p. 53-65 (2014)reponame:accedaCRIS portal de investigación de la Universidad de las Palmas de Gran Canariainstname:InglésLecture Notes in Computer Science1st International Workshop on Video Analytics for Audience Measurement (VAAM 2014)8811 LNCSinfo:eu-repo/semantics/openAccessoai:accedacris.ulpgc.es:10553/157532025-08-04T10:01:22Z
dc.title.none.fl_str_mv Evaluation of LBP and HOG descriptors for clothing attribute description
title Evaluation of LBP and HOG descriptors for clothing attribute description
spellingShingle Evaluation of LBP and HOG descriptors for clothing attribute description
Lorenzo Navarro, José Javier
120304 Inteligencia artificial
LBP
HOG
Clothing description
title_short Evaluation of LBP and HOG descriptors for clothing attribute description
title_full Evaluation of LBP and HOG descriptors for clothing attribute description
title_fullStr Evaluation of LBP and HOG descriptors for clothing attribute description
title_full_unstemmed Evaluation of LBP and HOG descriptors for clothing attribute description
title_sort Evaluation of LBP and HOG descriptors for clothing attribute description
dc.creator.none.fl_str_mv Lorenzo Navarro, José Javier
Castrillón-Santana, Modesto
Ramón Balmaseda, Enrique José
Freire, David
author Lorenzo Navarro, José Javier
author_facet Lorenzo Navarro, José Javier
Castrillón-Santana, Modesto
Ramón Balmaseda, Enrique José
Freire, David
author_role author
author2 Castrillón-Santana, Modesto
Ramón Balmaseda, Enrique José
Freire, David
author2_role author
author
author
dc.contributor.none.fl_str_mv 15042453800
22333278500
56494744200
35078304000
2489695
32145428
5871035
5069358
WOS:Lorenzo-Navarro, J
WOS:Castrillon, M
WOS:Ramon, E
WOS:Freire, D
dc.subject.none.fl_str_mv 120304 Inteligencia artificial
LBP
HOG
Clothing description
topic 120304 Inteligencia artificial
LBP
HOG
Clothing description
description In this work an experimental study about the capability of the LBP, HOG descriptors and color for clothing attribute classification is presented. Two different variants of the LBP descriptor are considered, the original LBP and the uniform LBP. Two classifiers, Linear SVM and Random Forest, have been included in the comparison because they have been frequently used in clothing attributes classification. The experiments are carried out with a public available dataset, the clothing attribute dataset, that has 26 attributes in total. The obtained accuracies are over 75% in most cases, reaching 80% for the necktie or sleeve length attributes.
publishDate 2014
dc.date.none.fl_str_mv 2014
2016
2016
2018
2018
Ener
dc.type.none.fl_str_mv info:eu-repo/semantics/bookPart
Book part
format bookPart
dc.identifier.none.fl_str_mv http://hdl.handle.net/10553/15753
url http://hdl.handle.net/10553/15753
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Lecture Notes in Computer Science
1st International Workshop on Video Analytics for Audience Measurement (VAAM 2014)
8811 LNCS
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Springer
publisher.none.fl_str_mv Springer
dc.source.none.fl_str_mv Video Analytics for Audience Measurement. VAAM 2014. Lecture Notes in Computer Science, v. 8811 LNCS, p. 53-65 (2014)
reponame:accedaCRIS portal de investigación de la Universidad de las Palmas de Gran Canaria
instname:
instname_str
reponame_str accedaCRIS portal de investigación de la Universidad de las Palmas de Gran Canaria
collection accedaCRIS portal de investigación de la Universidad de las Palmas de Gran Canaria
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869420090715275264
score 15,301629

Similares en LA Referencia