A cortical framework for invariant object categorization and recognition
Autor(a) principal: | |
---|---|
Data de Publicação: | 2009 |
Outros Autores: | |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.1/882 |
Resumo: | In this paper we present a new model for invariant object categorization and recognition. It is based on explicit multi-scale features: lines, edges and keypoints are extracted from responses of simple, complex and endstopped cells in cortical area V1, and keypoints are used to construct saliency maps for Focus-of-Attention. The model is a functional but dichotomous one, because keypoints are employed to model the “where” data stream, with dynamic routing of features from V1 to higher areas to obtain translation, rotation and size invariance, whereas lines and edges are employed in the “what” stream for object categorization and recognition. Furthermore, both the “where” and “what” pathways are dynamic in that information at coarse scales is employed first, after which information at progressively finer scales is added in order to refine the processes, i.e., both the dynamic feature routing and the categorization level. The construction of group and object templates, which are thought to be available in the prefrontal cortex with “what” and “where” components in PF46d and PF46v, is also illustrated. The model was tested in the framework of an integrated and biologically plausible architecture. |
id |
RCAP_cc89937128967b80801fde65a195fac1 |
---|---|
oai_identifier_str |
oai:sapientia.ualg.pt:10400.1/882 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
A cortical framework for invariant object categorization and recognitionVisão humanaIn this paper we present a new model for invariant object categorization and recognition. It is based on explicit multi-scale features: lines, edges and keypoints are extracted from responses of simple, complex and endstopped cells in cortical area V1, and keypoints are used to construct saliency maps for Focus-of-Attention. The model is a functional but dichotomous one, because keypoints are employed to model the “where” data stream, with dynamic routing of features from V1 to higher areas to obtain translation, rotation and size invariance, whereas lines and edges are employed in the “what” stream for object categorization and recognition. Furthermore, both the “where” and “what” pathways are dynamic in that information at coarse scales is employed first, after which information at progressively finer scales is added in order to refine the processes, i.e., both the dynamic feature routing and the categorization level. The construction of group and object templates, which are thought to be available in the prefrontal cortex with “what” and “where” components in PF46d and PF46v, is also illustrated. The model was tested in the framework of an integrated and biologically plausible architecture.SapientiaRodrigues, J. M. F.du Buf, J. M. H.2011-12-06T13:54:59Z20092011-12-05T16:59:40Z2009-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.1/882engRodrigues, João; du Buf, J. M. H. A cortical framework for invariant object categorization and recognition, Cognitive Processing, 10, 3, 243-261, 2009.1612-4782AUT: 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:RCAAP2023-07-24T10:11:44Zoai:sapientia.ualg.pt:10400.1/882Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T19:55:09.784891Repositório 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 |
A cortical framework for invariant object categorization and recognition |
title |
A cortical framework for invariant object categorization and recognition |
spellingShingle |
A cortical framework for invariant object categorization and recognition Rodrigues, J. M. F. Visão humana |
title_short |
A cortical framework for invariant object categorization and recognition |
title_full |
A cortical framework for invariant object categorization and recognition |
title_fullStr |
A cortical framework for invariant object categorization and recognition |
title_full_unstemmed |
A cortical framework for invariant object categorization and recognition |
title_sort |
A cortical framework for invariant object categorization 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 humana |
topic |
Visão humana |
description |
In this paper we present a new model for invariant object categorization and recognition. It is based on explicit multi-scale features: lines, edges and keypoints are extracted from responses of simple, complex and endstopped cells in cortical area V1, and keypoints are used to construct saliency maps for Focus-of-Attention. The model is a functional but dichotomous one, because keypoints are employed to model the “where” data stream, with dynamic routing of features from V1 to higher areas to obtain translation, rotation and size invariance, whereas lines and edges are employed in the “what” stream for object categorization and recognition. Furthermore, both the “where” and “what” pathways are dynamic in that information at coarse scales is employed first, after which information at progressively finer scales is added in order to refine the processes, i.e., both the dynamic feature routing and the categorization level. The construction of group and object templates, which are thought to be available in the prefrontal cortex with “what” and “where” components in PF46d and PF46v, is also illustrated. The model was tested in the framework of an integrated and biologically plausible architecture. |
publishDate |
2009 |
dc.date.none.fl_str_mv |
2009 2009-01-01T00:00:00Z 2011-12-06T13:54:59Z 2011-12-05T16:59:40Z |
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/10400.1/882 |
url |
http://hdl.handle.net/10400.1/882 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Rodrigues, João; du Buf, J. M. H. A cortical framework for invariant object categorization and recognition, Cognitive Processing, 10, 3, 243-261, 2009. 1612-4782 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 |
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_ |
1799133152752435200 |