Feedback and surround modulated boundary detection

Edges are key components of any visual scene to the extent that we can recognise objects merely by their silhouettes. The human visual system captures edge information through neurons in the visual cortex that are sensitive to both intensity discontinuities and particular orientations. The "cla...

ver descrição completa

Detalhes bibliográficos
Autores: Akbarinia, Arash|||0000-0002-4249-231X, Parraga, Carlos Alejandro|||0000-0002-3809-241X
Formato: artículo
Fecha de publicación:2018
País:España
Recursos:Universitat Autònoma de Barcelona
Repositorio:Dipòsit Digital de Documents de la UAB
Idioma:inglés
OAI Identifier:oai:ddd.uab.cat:275061
Acesso em linha:https://ddd.uab.cat/record/275061
https://dx.doi.org/urn:doi:10.1007/s11263-017-1035-5
Access Level:acceso abierto
Palavra-chave:Biologically-inspired vision
Boundary detection
Surround modulation
id ES_7e42480051becd02fa38bc3f4a57ce44
oai_identifier_str oai:ddd.uab.cat:275061
network_acronym_str ES
network_name_str España
repository_id_str
spelling Feedback and surround modulated boundary detectionAkbarinia, Arash|||0000-0002-4249-231XParraga, Carlos Alejandro|||0000-0002-3809-241XBiologically-inspired visionBoundary detectionSurround modulationEdges are key components of any visual scene to the extent that we can recognise objects merely by their silhouettes. The human visual system captures edge information through neurons in the visual cortex that are sensitive to both intensity discontinuities and particular orientations. The "classical approach" assumes that these cells are only responsive to the stimulus present within their receptive fields, however, recent studies demonstrate that surrounding regions and inter-areal feedback connections influence their responses significantly. In this work we propose a biologically-inspired edge detection model in which orientation selective neurons are represented through the first derivative of a Gaussian function resembling double-opponent cells in the primary visual cortex (V1). In our model we account for four kinds of receptive field surround, i.e. full, far, iso- and orthogonal-orientation, whose contributions are contrast-dependant. The output signal fromV1 is pooled in its perpendicular direction by larger V2 neurons employing a contrast-variant centre-surround kernel. We further introduce a feedback connection from higher-level visual areas to the lower ones. The results of our model on three benchmark datasets show a big improvement compared to the current non-learning and biologically-inspired state-of-the-art algorithms while being competitive to the learning-based methods. 22018-01-0120182018-01-01Articlehttp://purl.org/coar/resource_type/c_6501AMhttp://purl.org/coar/version/c_ab4af688f83e57aainfo:eu-repo/semantics/articleapplication/pdfhttps://ddd.uab.cat/record/275061https://dx.doi.org/urn:doi:10.1007/s11263-017-1035-5reponame:Dipòsit Digital de Documents de la UABinstname:Universitat Autònoma de BarcelonaInglésengMinisterio de Economía y Competitividad https://doi.org/10.13039/501100003329 TIN2013-41751-PMinisterio de Economía y Competitividad https://doi.org/10.13039/501100003329 TIN2013-49982-EXPopen accesshttp://purl.org/coar/access_right/c_abf2Aquest material està protegit per drets d'autor i/o drets afins. Podeu utilitzar aquest material en funció del que permet la legislació de drets d'autor i drets afins d'aplicació al vostre cas. Per a d'altres usos heu d'obtenir permís del(s) titular(s) de drets.https://rightsstatements.org/vocab/InC/1.0/info:eu-repo/semantics/openAccessoai:ddd.uab.cat:2750612026-06-06T12:50:31Z
dc.title.none.fl_str_mv Feedback and surround modulated boundary detection
title Feedback and surround modulated boundary detection
spellingShingle Feedback and surround modulated boundary detection
Akbarinia, Arash|||0000-0002-4249-231X
Biologically-inspired vision
Boundary detection
Surround modulation
title_short Feedback and surround modulated boundary detection
title_full Feedback and surround modulated boundary detection
title_fullStr Feedback and surround modulated boundary detection
title_full_unstemmed Feedback and surround modulated boundary detection
title_sort Feedback and surround modulated boundary detection
dc.creator.none.fl_str_mv Akbarinia, Arash|||0000-0002-4249-231X
Parraga, Carlos Alejandro|||0000-0002-3809-241X
author Akbarinia, Arash|||0000-0002-4249-231X
author_facet Akbarinia, Arash|||0000-0002-4249-231X
Parraga, Carlos Alejandro|||0000-0002-3809-241X
author_role author
author2 Parraga, Carlos Alejandro|||0000-0002-3809-241X
author2_role author
dc.subject.none.fl_str_mv Biologically-inspired vision
Boundary detection
Surround modulation
topic Biologically-inspired vision
Boundary detection
Surround modulation
description Edges are key components of any visual scene to the extent that we can recognise objects merely by their silhouettes. The human visual system captures edge information through neurons in the visual cortex that are sensitive to both intensity discontinuities and particular orientations. The "classical approach" assumes that these cells are only responsive to the stimulus present within their receptive fields, however, recent studies demonstrate that surrounding regions and inter-areal feedback connections influence their responses significantly. In this work we propose a biologically-inspired edge detection model in which orientation selective neurons are represented through the first derivative of a Gaussian function resembling double-opponent cells in the primary visual cortex (V1). In our model we account for four kinds of receptive field surround, i.e. full, far, iso- and orthogonal-orientation, whose contributions are contrast-dependant. The output signal fromV1 is pooled in its perpendicular direction by larger V2 neurons employing a contrast-variant centre-surround kernel. We further introduce a feedback connection from higher-level visual areas to the lower ones. The results of our model on three benchmark datasets show a big improvement compared to the current non-learning and biologically-inspired state-of-the-art algorithms while being competitive to the learning-based methods.
publishDate 2018
dc.date.none.fl_str_mv 2
2018-01-01
2018
2018-01-01
dc.type.none.fl_str_mv Article
http://purl.org/coar/resource_type/c_6501
AM
http://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://ddd.uab.cat/record/275061
https://dx.doi.org/urn:doi:10.1007/s11263-017-1035-5
url https://ddd.uab.cat/record/275061
https://dx.doi.org/urn:doi:10.1007/s11263-017-1035-5
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Ministerio de Economía y Competitividad https://doi.org/10.13039/501100003329 TIN2013-41751-P
Ministerio de Economía y Competitividad https://doi.org/10.13039/501100003329 TIN2013-49982-EXP
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
https://rightsstatements.org/vocab/InC/1.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
https://rightsstatements.org/vocab/InC/1.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Dipòsit Digital de Documents de la UAB
instname:Universitat Autònoma de Barcelona
instname_str Universitat Autònoma de Barcelona
reponame_str Dipòsit Digital de Documents de la UAB
collection Dipòsit Digital de Documents de la UAB
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869411722994909185
score 15.301629

Registos relacionados