Multi-scale keypoints in V1 and beyond: object segregation, scale selection, saliency maps and face detection
Autor(a) principal: | |
---|---|
Data de Publicação: | 2006 |
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/10400.1/181 |
Resumo: | End-stopped cells in cortical area V1, which combine outputs of complex cells tuned to different orientations, serve to detect line and edge crossings, singularities and points with large curvature. These cells can be used to construct retinotopic keypoint maps at different spatial scales (level-of-detail). The importance of the multi-scale keypoint representation is studied in this paper. It is shown that this representation provides very important information for object recognition and face detection. Different grouping operators can be used for object segregation and automatic scale selection. Saliency maps for focus-of-attention can be constructed. Such maps can be employed for face detection by grouping facial landmarks at eyes, nose and mouth. Although a face detector can be based on processing within area V1, it is argued that such an operator must be embedded into dorsal and ventral data streams, to and from higher cortical areas, for obtaining translation-, rotation- and scale-invariant detection. |
id |
RCAP_1cb18e85baa2a4790d955dbbfd35c4b9 |
---|---|
oai_identifier_str |
oai:sapientia.ualg.pt:10400.1/181 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Multi-scale keypoints in V1 and beyond: object segregation, scale selection, saliency maps and face detectionVisão computorizadaCórtex visualEnd-stopped cells in cortical area V1, which combine outputs of complex cells tuned to different orientations, serve to detect line and edge crossings, singularities and points with large curvature. These cells can be used to construct retinotopic keypoint maps at different spatial scales (level-of-detail). The importance of the multi-scale keypoint representation is studied in this paper. It is shown that this representation provides very important information for object recognition and face detection. Different grouping operators can be used for object segregation and automatic scale selection. Saliency maps for focus-of-attention can be constructed. Such maps can be employed for face detection by grouping facial landmarks at eyes, nose and mouth. Although a face detector can be based on processing within area V1, it is argued that such an operator must be embedded into dorsal and ventral data streams, to and from higher cortical areas, for obtaining translation-, rotation- and scale-invariant detection.ElsevierSapientiaRodrigues, J. M. F.du Buf, J. M. H.2009-02-13T17:10:06Z20062006-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.1/181engBYOSYSTEMSByoSystems. - Ireland : Elsevier. - Vol. 86, nº. 1-3 (October - December 2006), p. 75-90info: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:10400.1/181Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T19:54:35.381781Repositório 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 |
Multi-scale keypoints in V1 and beyond: object segregation, scale selection, saliency maps and face detection |
title |
Multi-scale keypoints in V1 and beyond: object segregation, scale selection, saliency maps and face detection |
spellingShingle |
Multi-scale keypoints in V1 and beyond: object segregation, scale selection, saliency maps and face detection Rodrigues, J. M. F. Visão computorizada Córtex visual |
title_short |
Multi-scale keypoints in V1 and beyond: object segregation, scale selection, saliency maps and face detection |
title_full |
Multi-scale keypoints in V1 and beyond: object segregation, scale selection, saliency maps and face detection |
title_fullStr |
Multi-scale keypoints in V1 and beyond: object segregation, scale selection, saliency maps and face detection |
title_full_unstemmed |
Multi-scale keypoints in V1 and beyond: object segregation, scale selection, saliency maps and face detection |
title_sort |
Multi-scale keypoints in V1 and beyond: object segregation, scale selection, saliency maps and face detection |
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 |
topic |
Visão computorizada Córtex visual |
description |
End-stopped cells in cortical area V1, which combine outputs of complex cells tuned to different orientations, serve to detect line and edge crossings, singularities and points with large curvature. These cells can be used to construct retinotopic keypoint maps at different spatial scales (level-of-detail). The importance of the multi-scale keypoint representation is studied in this paper. It is shown that this representation provides very important information for object recognition and face detection. Different grouping operators can be used for object segregation and automatic scale selection. Saliency maps for focus-of-attention can be constructed. Such maps can be employed for face detection by grouping facial landmarks at eyes, nose and mouth. Although a face detector can be based on processing within area V1, it is argued that such an operator must be embedded into dorsal and ventral data streams, to and from higher cortical areas, for obtaining translation-, rotation- and scale-invariant detection. |
publishDate |
2006 |
dc.date.none.fl_str_mv |
2006 2006-01-01T00:00:00Z 2009-02-13T17:10:06Z |
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/10400.1/181 |
url |
http://hdl.handle.net/10400.1/181 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
BYOSYSTEMSByoSystems. - Ireland : Elsevier. - Vol. 86, nº. 1-3 (October - December 2006), p. 75-90 |
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.publisher.none.fl_str_mv |
Elsevier |
publisher.none.fl_str_mv |
Elsevier |
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_ |
1799133144898600960 |