A NOVEL TEXTURE CLASSIFICATION METHOD BASED ON HESSIAN MATRIX AND PRINCIPAL CURVATURES

Basit Öğe Kaydı
dc.authoridHanbay, Davut/0000-0003-2271-7865
dc.authoridTalu, Muhammed Fatih/0000-0003-1166-8404
dc.authoridHanbay, Kazım/0000-0003-1374-1417
dc.authoridALPASLAN, Nuh/0000-0002-6828-755X
dc.authorwosidHanbay, Davut/AAG-8511-2019
dc.authorwosidTalu, Muhammed Fatih/W-2834-2017
dc.authorwosidHanbay, Kazım/J-3848-2014
dc.authorwosidALPASLAN, Nuh/B-2199-2018
dc.contributor.authorAlpaslan, Nuh
dc.contributor.authorHanbay, Kazim
dc.contributor.authorHanbay, Davut
dc.contributor.authorTalu, M. Fatih
dc.date.accessioned2024-08-04T20:56:20Z
dc.date.available2024-08-04T20:56:20Z
dc.date.issued2014
dc.departmentİnönü Üniversitesien_US
dc.description22nd IEEE Signal Processing and Communications Applications Conference (SIU) -- APR 23-25, 2014 -- Karadeniz Teknik Univ, Trabzon, TURKEYen_US
dc.description.abstractIn this study, in order to obtain similar effect with conventional gradient operation and extract more robust feature for texture, we use the principal curvature informations instead of the gradient calculation. Through this methods, sharp and important informations about the texture images were obtained by analyzing images of the second order. Considering the classification results obtained, it is shown that the proposed method improve the performance of original CoHOG and HOG feature extraction methods. As a result of experiments on datasets with different characteristics, it is seen that, the proposed method has higher classification performance.en_US
dc.description.sponsorshipIEEE,Karadeniz Tech Univ, Dept Comp Engn & Elect & Elect Engnen_US
dc.identifier.endpage163en_US
dc.identifier.isbn978-1-4799-4874-1
dc.identifier.issn2165-0608
dc.identifier.startpage160en_US
dc.identifier.urihttps://hdl.handle.net/11616/102221
dc.identifier.wosWOS:000356351400020en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.language.isotren_US
dc.publisherIeeeen_US
dc.relation.ispartof2014 22nd Signal Processing and Communications Applications Conference (Siu)en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectHOGen_US
dc.subjectCoHOGen_US
dc.subjectHessian matrisen_US
dc.subjectTemel Egrilikleren_US
dc.titleA NOVEL TEXTURE CLASSIFICATION METHOD BASED ON HESSIAN MATRIX AND PRINCIPAL CURVATURESen_US
dc.typeConference Objecten_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu