Show simple item record

dc.contributor.authorHanbay, K. and Alpaslan, N. and Talu, M.F. and Hanbay, D.
dc.date.accessioned2021-04-08T12:08:31Z
dc.date.available2021-04-08T12:08:31Z
dc.date.issued2016
dc.identifier10.1016/j.neucom.2016.03.032
dc.identifier.issn09252312
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-84978319136&doi=10.1016%2fj.neucom.2016.03.032&partnerID=40&md5=1f6356ffd696b7376f48b0526701d00e
dc.identifier.urihttp://acikerisim.bingol.edu.tr/handle/20.500.12898/4628
dc.description.abstractThe histograms of oriented gradients (HOG) and co-occurrence HOG (CoHOG) algorithms are simple and intuitive descriptors. However, the HOG and CoHOG algorithms based on gradient computation still have some shortcomings: they ignore meaningful textural properties and are unstable to noise. In this paper, two new efficient HOG and CoHOG methods are proposed. The proposed algorithms are based on the Gaussian derivative filters, and the feature vectors are obtained by means of principal curvatures. The feature vectors are rotation invariant by means of the rotation invariance characteristic of principal curvatures (i.e. eigenvalues). The experimental results on the CUReT, KTH-TIPS, KTH-TIPS2-a, UIUC, Brodatz album, Kylberg and Xu datasets confirm that the developed algorithms have higher classification rates than state-of-the-art texture classification methods. The classification results also demonstrate that the developed algorithms are more stable to noise and rotation than the original HOG and CoHOG algorithms. © 2016 Elsevier B.V.
dc.language.isoEnglish
dc.sourceNeurocomputing
dc.titlePrincipal curvatures based rotation invariant algorithms for efficient texture classification


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record