Multi-scale keypoints in V1 and face detection
Autor(a) principal: | |
---|---|
Data de Publicação: | 2005 |
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/10400.1/36 |
Resumo: | End-stopped cells in cortical area V1, which combine out- puts of complex cells tuned to different orientations, serve to detect line and edge crossings (junctions) and points with a large curvature. In this paper we study the importance of the multi-scale keypoint representa- tion, i.e. retinotopic keypoint maps which are tuned to different spatial frequencies (scale or Level-of-Detail). We show that this representation provides important information for Focus-of-Attention (FoA) and object detection. In particular, we show that hierarchically-structured saliency maps for FoA can be obtained, and that combinations over scales in conjunction with spatial symmetries can lead to face detection through grouping operators that deal with keypoints at the eyes, nose and mouth, especially when non-classical receptive field inhibition is employed. Al- though a face detector can be based on feedforward and feedback loops within area V1, such an operator must be embedded into dorsal and ventral data streams to and from higher areas for obtaining translation-, rotation- and scale-invariant face (object) detection. |
id |
RCAP_9690c1271ddd18de2f37b3f53ad8ad16 |
---|---|
oai_identifier_str |
oai:sapientia.ualg.pt:10400.1/36 |
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 face detectionVisão computorizadaCórtex visualEnd-stopped cells in cortical area V1, which combine out- puts of complex cells tuned to different orientations, serve to detect line and edge crossings (junctions) and points with a large curvature. In this paper we study the importance of the multi-scale keypoint representa- tion, i.e. retinotopic keypoint maps which are tuned to different spatial frequencies (scale or Level-of-Detail). We show that this representation provides important information for Focus-of-Attention (FoA) and object detection. In particular, we show that hierarchically-structured saliency maps for FoA can be obtained, and that combinations over scales in conjunction with spatial symmetries can lead to face detection through grouping operators that deal with keypoints at the eyes, nose and mouth, especially when non-classical receptive field inhibition is employed. Al- though a face detector can be based on feedforward and feedback loops within area V1, such an operator must be embedded into dorsal and ventral data streams to and from higher areas for obtaining translation-, rotation- and scale-invariant face (object) detection.NaplesSapientiaRodrigues, J. M. F.du Buf, J. M. H.2009-02-13T17:09:10Z20052005-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfapplication/pdfhttp://hdl.handle.net/10400.1/36eng1st International Symposium Brain, Vision and Artificial Intell. (BV&AI 2005) . - Naples, 19-21 October 2005. - LNCS 3704. - p. 205-214AUT: 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:RCAAP2023-07-24T10:10:45Zoai:sapientia.ualg.pt:10400.1/36Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T19:54:28.785713Repositório 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 face detection |
title |
Multi-scale keypoints in V1 and face detection |
spellingShingle |
Multi-scale keypoints in V1 and face detection Rodrigues, J. M. F. Visão computorizada Córtex visual |
title_short |
Multi-scale keypoints in V1 and face detection |
title_full |
Multi-scale keypoints in V1 and face detection |
title_fullStr |
Multi-scale keypoints in V1 and face detection |
title_full_unstemmed |
Multi-scale keypoints in V1 and face detection |
title_sort |
Multi-scale keypoints in V1 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 out- puts of complex cells tuned to different orientations, serve to detect line and edge crossings (junctions) and points with a large curvature. In this paper we study the importance of the multi-scale keypoint representa- tion, i.e. retinotopic keypoint maps which are tuned to different spatial frequencies (scale or Level-of-Detail). We show that this representation provides important information for Focus-of-Attention (FoA) and object detection. In particular, we show that hierarchically-structured saliency maps for FoA can be obtained, and that combinations over scales in conjunction with spatial symmetries can lead to face detection through grouping operators that deal with keypoints at the eyes, nose and mouth, especially when non-classical receptive field inhibition is employed. Al- though a face detector can be based on feedforward and feedback loops within area V1, such an operator must be embedded into dorsal and ventral data streams to and from higher areas for obtaining translation-, rotation- and scale-invariant face (object) detection. |
publishDate |
2005 |
dc.date.none.fl_str_mv |
2005 2005-01-01T00:00:00Z 2009-02-13T17:09:10Z |
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/10400.1/36 |
url |
http://hdl.handle.net/10400.1/36 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
1st International Symposium Brain, Vision and Artificial Intell. (BV&AI 2005) . - Naples, 19-21 October 2005. - LNCS 3704. - p. 205-214 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 |
Naples |
publisher.none.fl_str_mv |
Naples |
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_ |
1799133144167743488 |