A brief analysis of the dense extreme inception network for edge detection
This work describes DexiNed, a Dense Extreme Inception Network for Edge Detection proposed by Xavier Soria, Edgar Riba and Angel Sappa in [IEEE Winter Conference on Applications of Computer Vision (WACV), 2020]. The network is organized in blocks that extract edges at different resolutions, which ar...
| Authors: | ; |
|---|---|
| Format: | Article |
| Status: | Published version |
| Publication date: | 2022 |
| Country: | Uruguay |
| Institution: | Universidad de la República |
| Repository: | COLIBRI |
| Language: | English |
| OAI Identifier: | oai:colibri.udelar.edu.uy:20.500.12008/34134 |
| Online Access: | https://www.ipol.im/pub/art/2022/423/ https://hdl.handle.net/20.500.12008/34134 |
| Access Level: | Open access |
| Keyword: | Image edge detection Neural network HED Xception |
| _version_ | 1878413326123270144 |
|---|---|
| author | Grompone von Gioi, Rafael |
| author2 | Randall, Gregory |
| author2_role | author |
| author_browse | Grompone von Gioi, Rafael Randall, Gregory |
| author_facet | Grompone von Gioi, Rafael Randall, Gregory |
| author_role | author |
| bitstream_url_str_mv | http://localhost:8080/xmlui/bitstream/20.500.12008/34134/5/license.txt http://localhost:8080/xmlui/bitstream/20.500.12008/34134/2/license_url http://localhost:8080/xmlui/bitstream/20.500.12008/34134/3/license_text http://localhost:8080/xmlui/bitstream/20.500.12008/34134/4/license_rdf http://localhost:8080/xmlui/bitstream/20.500.12008/34134/1/GR22a.pdf |
| collection | COLIBRI |
| description | This work describes DexiNed, a Dense Extreme Inception Network for Edge Detection proposed by Xavier Soria, Edgar Riba and Angel Sappa in [IEEE Winter Conference on Applications of Computer Vision (WACV), 2020]. The network is organized in blocks that extract edges at different resolutions, which are then merged to produce a multiscale edge map. For training, the authors introduced an annotated dataset (BIPED) specifically designed for edge detection. We perform a brief analysis of the results produced by DexiNed, highlighting its quality but also indicating its limitations. Overall, DexiNed produces state-of-the-art results. |
| eu_rights_str_mv | openAccess |
| format | article |
| id | UY_3f2d8d64f83c59d301ed8cf6fc01acaa |
| identifier_str_mv | 10.5201/ipol.2022.423 |
| institution | Universidad de la República |
| instname_str | Universidad de la República |
| language | eng |
| network_acronym_str | UY |
| network_name_str | Uruguay |
| oai_identifier_str | oai:colibri.udelar.edu.uy:20.500.12008/34134 |
| publishDate | 2022 |
| publishDateSort | 2022 |
| publisher | Centre Borelli, ENS Paris-Saclay; DMI, Universitat de les Illes Balears; Fing, Universidad de la República. |
| publisherStr | Centre Borelli, ENS Paris-Saclay; DMI, Universitat de les Illes Balears; Fing, Universidad de la República. |
| reponame_str | COLIBRI |
| spelling | A brief analysis of the dense extreme inception network for edge detection Grompone von Gioi, Rafael Randall, Gregory Image edge detection Neural network HED Xception This work describes DexiNed, a Dense Extreme Inception Network for Edge Detection proposed by Xavier Soria, Edgar Riba and Angel Sappa in [IEEE Winter Conference on Applications of Computer Vision (WACV), 2020]. The network is organized in blocks that extract edges at different resolutions, which are then merged to produce a multiscale edge map. For training, the authors introduced an annotated dataset (BIPED) specifically designed for edge detection. We perform a brief analysis of the results produced by DexiNed, highlighting its quality but also indicating its limitations. Overall, DexiNed produces state-of-the-art results. Submitted by Ribeiro Jorge (jribeiro@fing.edu.uy) on 2022-10-11T19:07:10Z No. of bitstreams: 2 license_rdf: 23749 bytes, checksum: 6a69abe32f6fabdffa4c61be8f8efebd (MD5) GR22a.pdf: 29240450 bytes, checksum: 9a119fc5dfa819bf65578e48b2f20d8f (MD5) Approved for entry into archive by Machado Jimena (jmachado@fing.edu.uy) on 2022-10-12T18:23:50Z (GMT) No. of bitstreams: 2 license_rdf: 23749 bytes, checksum: 6a69abe32f6fabdffa4c61be8f8efebd (MD5) GR22a.pdf: 29240450 bytes, checksum: 9a119fc5dfa819bf65578e48b2f20d8f (MD5) Made available in DSpace by Luna Fabiana (fabiana.luna@seciu.edu.uy) on 2022-10-13T12:25:16Z (GMT). No. of bitstreams: 2 license_rdf: 23749 bytes, checksum: 6a69abe32f6fabdffa4c61be8f8efebd (MD5) GR22a.pdf: 29240450 bytes, checksum: 9a119fc5dfa819bf65578e48b2f20d8f (MD5) Previous issue date: 2022 Centre Borelli, ENS Paris-Saclay; DMI, Universitat de les Illes Balears; Fing, Universidad de la República. Grompone von Gioi, R y Randall, G. "A brief analysis of the dense extreme inception network for edge detection". IPOL. Journal Image Processing On Line. [en línea]. 2022, no 12, pp. 389-403. DOI: 10.5201/ipol.2022.423 2105–1232 https://www.ipol.im/pub/art/2022/423/ https://hdl.handle.net/20.500.12008/34134 10.5201/ipol.2022.423 |
| spellingShingle | A brief analysis of the dense extreme inception network for edge detection Grompone von Gioi, Rafael Image edge detection Neural network HED Xception |
| status_str | publishedVersion |
| title | A brief analysis of the dense extreme inception network for edge detection |
| title_full | A brief analysis of the dense extreme inception network for edge detection |
| title_fullStr | A brief analysis of the dense extreme inception network for edge detection |
| title_full_unstemmed | A brief analysis of the dense extreme inception network for edge detection |
| title_short | A brief analysis of the dense extreme inception network for edge detection |
| title_sort | A brief analysis of the dense extreme inception network for edge detection |
| topic | Image edge detection Neural network HED Xception |
| topic_facet | Image edge detection Neural network HED Xception |
| url | https://www.ipol.im/pub/art/2022/423/ https://hdl.handle.net/20.500.12008/34134 |