SymPaD: Symbolic patch descriptor

dc.contributor.authorAslan S.
dc.contributor.authorAkgül C.B.
dc.contributor.authorSankur B.
dc.contributor.authorTunali E.T.
dc.date.accessioned2019-10-26T21:26:18Z
dc.date.available2019-10-26T21:26:18Z
dc.date.issued2015
dc.departmentEge Üniversitesien_US
dc.descriptionInstitute for Systems and Technologies of Information, Control and Communication (INSTICC)en_US
dc.description10th International Conference on Computer Vision Theory and Applications, VISAPP 2015 -- 11 March 2015 through 14 March 2015 -- 112690en_US
dc.description.abstractWe 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.endpage271en_US
dc.identifier.isbn9789897580895
dc.identifier.scopusqualityN/Aen_US
dc.identifier.startpage266en_US
dc.identifier.urihttps://hdl.handle.net/11454/17333
dc.identifier.volume1en_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherSciTePressen_US
dc.relation.ispartofVISAPP 2015 - 10th International Conference on Computer Vision Theory and Applications; VISIGRAPP, Proceedingsen_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectImage featureen_US
dc.subjectImage understandingen_US
dc.subjectModel-driven visual dictionaryen_US
dc.subjectObject recognitionen_US
dc.subjectPrimitive structures of natural imagesen_US
dc.titleSymPaD: Symbolic patch descriptoren_US
dc.typeConference Objecten_US

Dosyalar