A brief analysis of the holistically-nested edge detector

Grompone von Gioi, Rafael - Randall, Gregory

Resumen:

This work describes the HED method for edge detection. HED uses a neural network based on a VGG16 backbone, supplemented with some extra layers for merging the results at different scales. The training was performed on an augmented version of the BSDS500 dataset. We perform a brief analysis of the results produced by HED, highlighting its quality but also indicating its limitations. Overall, HED produces state-of-the-art results.


Detalles Bibliográficos
2022
Image edge detection
Neural network
VGG16
Inglés
Universidad de la República
COLIBRI
https://www.ipol.im/pub/art/2022/422/
https://hdl.handle.net/20.500.12008/34071
Acceso abierto
Licencia Creative Commons Atribución - No Comercial - Compartir Igual (CC - By-NC-SA 4.0)
_version_ 1807522899455639552
author Grompone von Gioi, Rafael
author2 Randall, Gregory
author2_role author
author_facet Grompone von Gioi, Rafael
Randall, Gregory
author_role author
bitstream.checksum.fl_str_mv 6429389a7df7277b72b7924fdc7d47a9
a9ac1bac94fe38dbe560422d834a993f
336de3b3b01611d7eba286b6ddc14579
6a69abe32f6fabdffa4c61be8f8efebd
8300eaa1c43e6e41ec035e277de0f6a4
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
MD5
bitstream.url.fl_str_mv http://localhost:8080/xmlui/bitstream/20.500.12008/34071/5/license.txt
http://localhost:8080/xmlui/bitstream/20.500.12008/34071/2/license_url
http://localhost:8080/xmlui/bitstream/20.500.12008/34071/3/license_text
http://localhost:8080/xmlui/bitstream/20.500.12008/34071/4/license_rdf
http://localhost:8080/xmlui/bitstream/20.500.12008/34071/1/GR22.pdf
collection COLIBRI
dc.contributor.filiacion.none.fl_str_mv Grompone von Gioi Rafael, Université Paris-Saclay, France
Randall Gregory, Universidad de la República (Uruguay). Facultad de Ingeniería.
dc.creator.none.fl_str_mv Grompone von Gioi, Rafael
Randall, Gregory
dc.date.accessioned.none.fl_str_mv 2022-10-11T12:15:20Z
dc.date.available.none.fl_str_mv 2022-10-11T12:15:20Z
dc.date.issued.none.fl_str_mv 2022
dc.description.abstract.none.fl_txt_mv This work describes the HED method for edge detection. HED uses a neural network based on a VGG16 backbone, supplemented with some extra layers for merging the results at different scales. The training was performed on an augmented version of the BSDS500 dataset. We perform a brief analysis of the results produced by HED, highlighting its quality but also indicating its limitations. Overall, HED produces state-of-the-art results.
dc.description.es.fl_txt_mv Este artículo está disponible en línea con materiales complementarios, software, conjuntos de datos y demostración en https://doi.org/10.5201/ipol.2022.422
dc.format.extent.es.fl_str_mv 9 p.
dc.format.mimetype.es.fl_str_mv application/pdf
dc.identifier.citation.es.fl_str_mv Grompone von Gioi, R. y Randall, G. "A brief analysis of the holistically-nested edge detector". IPOL. Journal Image Processing On Line. [en línea]. 2022, no 12, pp. 369-377. DOI: 10.5201/ipol.2022.422
dc.identifier.doi.none.fl_str_mv 10.5201/ipol.2022.422
dc.identifier.issn.none.fl_str_mv 2105–1232
dc.identifier.uri.none.fl_str_mv https://www.ipol.im/pub/art/2022/422/
https://hdl.handle.net/20.500.12008/34071
dc.language.iso.none.fl_str_mv en
eng
dc.publisher.es.fl_str_mv Centre Borelli, ENS Paris-Saclay; DMI, Universitat de les Illes Balears; Fing, Universidad de la República.
dc.relation.ispartof.es.fl_str_mv IPOL. Journal Image Processing On Line, no 12, Oct 2022, pp. 369-377
dc.rights.license.none.fl_str_mv Licencia Creative Commons Atribución - No Comercial - Compartir Igual (CC - By-NC-SA 4.0)
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
dc.source.none.fl_str_mv reponame:COLIBRI
instname:Universidad de la República
instacron:Universidad de la República
dc.subject.es.fl_str_mv Image edge detection
Neural network
VGG16
dc.title.none.fl_str_mv A brief analysis of the holistically-nested edge detector
dc.type.es.fl_str_mv Artículo
dc.type.none.fl_str_mv info:eu-repo/semantics/article
dc.type.version.none.fl_str_mv info:eu-repo/semantics/publishedVersion
description Este artículo está disponible en línea con materiales complementarios, software, conjuntos de datos y demostración en https://doi.org/10.5201/ipol.2022.422
eu_rights_str_mv openAccess
format article
id COLIBRI_02f36c53c47087323b1b19f24a08d66c
identifier_str_mv Grompone von Gioi, R. y Randall, G. "A brief analysis of the holistically-nested edge detector". IPOL. Journal Image Processing On Line. [en línea]. 2022, no 12, pp. 369-377. DOI: 10.5201/ipol.2022.422
2105–1232
10.5201/ipol.2022.422
instacron_str Universidad de la República
institution Universidad de la República
instname_str Universidad de la República
language eng
language_invalid_str_mv en
network_acronym_str COLIBRI
network_name_str COLIBRI
oai_identifier_str oai:colibri.udelar.edu.uy:20.500.12008/34071
publishDate 2022
reponame_str COLIBRI
repository.mail.fl_str_mv mabel.seroubian@seciu.edu.uy
repository.name.fl_str_mv COLIBRI - Universidad de la República
repository_id_str 4771
rights_invalid_str_mv Licencia Creative Commons Atribución - No Comercial - Compartir Igual (CC - By-NC-SA 4.0)
spelling Grompone von Gioi Rafael, Université Paris-Saclay, FranceRandall Gregory, Universidad de la República (Uruguay). Facultad de Ingeniería.2022-10-11T12:15:20Z2022-10-11T12:15:20Z2022Grompone von Gioi, R. y Randall, G. "A brief analysis of the holistically-nested edge detector". IPOL. Journal Image Processing On Line. [en línea]. 2022, no 12, pp. 369-377. DOI: 10.5201/ipol.2022.4222105–1232https://www.ipol.im/pub/art/2022/422/https://hdl.handle.net/20.500.12008/3407110.5201/ipol.2022.422Este artículo está disponible en línea con materiales complementarios, software, conjuntos de datos y demostración en https://doi.org/10.5201/ipol.2022.422This work describes the HED method for edge detection. HED uses a neural network based on a VGG16 backbone, supplemented with some extra layers for merging the results at different scales. The training was performed on an augmented version of the BSDS500 dataset. We perform a brief analysis of the results produced by HED, highlighting its quality but also indicating its limitations. Overall, HED produces state-of-the-art results.Submitted by Ribeiro Jorge (jribeiro@fing.edu.uy) on 2022-10-03T17:19:34Z No. of bitstreams: 2 license_rdf: 23749 bytes, checksum: 6a69abe32f6fabdffa4c61be8f8efebd (MD5) GR22.pdf: 1810886 bytes, checksum: 8300eaa1c43e6e41ec035e277de0f6a4 (MD5)Approved for entry into archive by Machado Jimena (jmachado@fing.edu.uy) on 2022-10-03T18:37:53Z (GMT) No. of bitstreams: 2 license_rdf: 23749 bytes, checksum: 6a69abe32f6fabdffa4c61be8f8efebd (MD5) GR22.pdf: 1810886 bytes, checksum: 8300eaa1c43e6e41ec035e277de0f6a4 (MD5)Made available in DSpace by Luna Fabiana (fabiana.luna@seciu.edu.uy) on 2022-10-11T12:15:20Z (GMT). No. of bitstreams: 2 license_rdf: 23749 bytes, checksum: 6a69abe32f6fabdffa4c61be8f8efebd (MD5) GR22.pdf: 1810886 bytes, checksum: 8300eaa1c43e6e41ec035e277de0f6a4 (MD5) Previous issue date: 20229 p.application/pdfenengCentre Borelli, ENS Paris-Saclay; DMI, Universitat de les Illes Balears; Fing, Universidad de la República.IPOL. Journal Image Processing On Line, no 12, Oct 2022, pp. 369-377Las obras depositadas en el Repositorio se rigen por la Ordenanza de los Derechos de la Propiedad Intelectual de la Universidad de la República.(Res. Nº 91 de C.D.C. de 8/III/1994 – D.O. 7/IV/1994) y por la Ordenanza del Repositorio Abierto de la Universidad de la República (Res. Nº 16 de C.D.C. de 07/10/2014)info:eu-repo/semantics/openAccessLicencia Creative Commons Atribución - No Comercial - Compartir Igual (CC - By-NC-SA 4.0)Image edge detectionNeural networkVGG16A brief analysis of the holistically-nested edge detectorArtículoinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionreponame:COLIBRIinstname:Universidad de la Repúblicainstacron:Universidad de la RepúblicaGrompone von Gioi, RafaelRandall, GregoryProcesamiento de SeñalesTratamiento de ImágenesLICENSElicense.txtlicense.txttext/plain; charset=utf-84267http://localhost:8080/xmlui/bitstream/20.500.12008/34071/5/license.txt6429389a7df7277b72b7924fdc7d47a9MD55CC-LICENSElicense_urllicense_urltext/plain; charset=utf-850http://localhost:8080/xmlui/bitstream/20.500.12008/34071/2/license_urla9ac1bac94fe38dbe560422d834a993fMD52license_textlicense_texttext/html; charset=utf-838884http://localhost:8080/xmlui/bitstream/20.500.12008/34071/3/license_text336de3b3b01611d7eba286b6ddc14579MD53license_rdflicense_rdfapplication/rdf+xml; charset=utf-823749http://localhost:8080/xmlui/bitstream/20.500.12008/34071/4/license_rdf6a69abe32f6fabdffa4c61be8f8efebdMD54ORIGINALGR22.pdfGR22.pdfapplication/pdf1810886http://localhost:8080/xmlui/bitstream/20.500.12008/34071/1/GR22.pdf8300eaa1c43e6e41ec035e277de0f6a4MD5120.500.12008/340712024-07-24 17:25:46.542oai:colibri.udelar.edu.uy:20.500.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Universidadhttps://udelar.edu.uy/https://www.colibri.udelar.edu.uy/oai/requestmabel.seroubian@seciu.edu.uyUruguayopendoar:47712024-07-25T14:33:18.030377COLIBRI - Universidad de la Repúblicafalse
spellingShingle A brief analysis of the holistically-nested edge detector
Grompone von Gioi, Rafael
Image edge detection
Neural network
VGG16
status_str publishedVersion
title A brief analysis of the holistically-nested edge detector
title_full A brief analysis of the holistically-nested edge detector
title_fullStr A brief analysis of the holistically-nested edge detector
title_full_unstemmed A brief analysis of the holistically-nested edge detector
title_short A brief analysis of the holistically-nested edge detector
title_sort A brief analysis of the holistically-nested edge detector
topic Image edge detection
Neural network
VGG16
url https://www.ipol.im/pub/art/2022/422/
https://hdl.handle.net/20.500.12008/34071

Resultados similares