Invariant multi-scale object categorisation and recognition

Detalhes bibliográficos
Autor(a) principal: Rodrigues, J. M. F.
Data de Publicação: 2007
Outros Autores: du Buf, J. M. H.
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10400.1/169
Resumo: Object recognition requires that templates with canonical views are stored in memory. Such templates must somehow be normalised. In this paper we present a novel method for obtaining 2D translation, rotation and size invariance. Cortical simple, complex and end-stopped cells provide multi-scale maps of lines, edges and keypoints. These maps are combined such that objects are characterised. Dynamic routing in neighbouring neural layers allows feature maps of input objects and stored templates to converge. We illustrate the construction of group templates and the invariance method for object categorisation and recognition in the context of a cortical architecture, which can be applied in computer vision.
id RCAP_8df20ee402bfe21a801eb948453f2af4
oai_identifier_str oai:sapientia.ualg.pt:10400.1/169
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Invariant multi-scale object categorisation and recognitionVisão computorizadaCórtex visual621.38Object recognition requires that templates with canonical views are stored in memory. Such templates must somehow be normalised. In this paper we present a novel method for obtaining 2D translation, rotation and size invariance. Cortical simple, complex and end-stopped cells provide multi-scale maps of lines, edges and keypoints. These maps are combined such that objects are characterised. Dynamic routing in neighbouring neural layers allows feature maps of input objects and stored templates to converge. We illustrate the construction of group templates and the invariance method for object categorisation and recognition in the context of a cortical architecture, which can be applied in computer vision.GironaSapientiaRodrigues, J. M. F.du Buf, J. M. H.2009-02-13T17:10:01Z20072007-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfapplication/pdfhttp://hdl.handle.net/10400.1/169eng3rd Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA 07). - Girona, 6 - 8 June 2007. - LNCS 4477. - p. 459-466AUT: JRO00913; DUB00865;info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-07-24T10:10:54Zoai:sapientia.ualg.pt:10400.1/169Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T19:54:34.769309Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Invariant multi-scale object categorisation and recognition
title Invariant multi-scale object categorisation and recognition
spellingShingle Invariant multi-scale object categorisation and recognition
Rodrigues, J. M. F.
Visão computorizada
Córtex visual
621.38
title_short Invariant multi-scale object categorisation and recognition
title_full Invariant multi-scale object categorisation and recognition
title_fullStr Invariant multi-scale object categorisation and recognition
title_full_unstemmed Invariant multi-scale object categorisation and recognition
title_sort Invariant multi-scale object categorisation and recognition
author Rodrigues, J. M. F.
author_facet Rodrigues, J. M. F.
du Buf, J. M. H.
author_role author
author2 du Buf, J. M. H.
author2_role author
dc.contributor.none.fl_str_mv Sapientia
dc.contributor.author.fl_str_mv Rodrigues, J. M. F.
du Buf, J. M. H.
dc.subject.por.fl_str_mv Visão computorizada
Córtex visual
621.38
topic Visão computorizada
Córtex visual
621.38
description Object recognition requires that templates with canonical views are stored in memory. Such templates must somehow be normalised. In this paper we present a novel method for obtaining 2D translation, rotation and size invariance. Cortical simple, complex and end-stopped cells provide multi-scale maps of lines, edges and keypoints. These maps are combined such that objects are characterised. Dynamic routing in neighbouring neural layers allows feature maps of input objects and stored templates to converge. We illustrate the construction of group templates and the invariance method for object categorisation and recognition in the context of a cortical architecture, which can be applied in computer vision.
publishDate 2007
dc.date.none.fl_str_mv 2007
2007-01-01T00:00:00Z
2009-02-13T17:10:01Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10400.1/169
url http://hdl.handle.net/10400.1/169
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 3rd Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA 07). - Girona, 6 - 8 June 2007. - LNCS 4477. - p. 459-466
AUT: JRO00913; DUB00865;
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Girona
publisher.none.fl_str_mv Girona
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799133144870289408

Registros relacionados