SymPaD: Symbolic patch descriptor
dc.contributor.author | Aslan S. | |
dc.contributor.author | Akgül C.B. | |
dc.contributor.author | Sankur B. | |
dc.contributor.author | Tunali E.T. | |
dc.date.accessioned | 2019-10-26T21:26:18Z | |
dc.date.available | 2019-10-26T21:26:18Z | |
dc.date.issued | 2015 | |
dc.department | Ege Üniversitesi | en_US |
dc.description | Institute for Systems and Technologies of Information, Control and Communication (INSTICC) | en_US |
dc.description | 10th International Conference on Computer Vision Theory and Applications, VISAPP 2015 -- 11 March 2015 through 14 March 2015 -- 112690 | en_US |
dc.description.abstract | We propose a new local image descriptor named SymPaD for image understanding. SymPaD is a probability vector associated with a given image pixel and represents the attachment of the pixel to a previously designed shape repertoire. As such the approach is model-driven. The SymPad descriptor is illumination and rotation invariant, and extremely flexible on extending the repertoire with any parametrically generated geometrical shapes and any desired additional transformation types. Copyright © 2015 SCITEPRESS - Science and Technology Publications All rights reserved. | en_US |
dc.identifier.endpage | 271 | en_US |
dc.identifier.isbn | 9789897580895 | |
dc.identifier.scopusquality | N/A | en_US |
dc.identifier.startpage | 266 | en_US |
dc.identifier.uri | https://hdl.handle.net/11454/17333 | |
dc.identifier.volume | 1 | en_US |
dc.indekslendigikaynak | Scopus | en_US |
dc.language.iso | en | en_US |
dc.publisher | SciTePress | en_US |
dc.relation.ispartof | VISAPP 2015 - 10th International Conference on Computer Vision Theory and Applications; VISIGRAPP, Proceedings | en_US |
dc.relation.publicationcategory | Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı | en_US |
dc.rights | info:eu-repo/semantics/closedAccess | en_US |
dc.subject | Image feature | en_US |
dc.subject | Image understanding | en_US |
dc.subject | Model-driven visual dictionary | en_US |
dc.subject | Object recognition | en_US |
dc.subject | Primitive structures of natural images | en_US |
dc.title | SymPaD: Symbolic patch descriptor | en_US |
dc.type | Conference Object | en_US |