Alpaslan, NuhHanbay, KazimHanbay, DavutTalu, M. Fatih2024-08-042024-08-042014978-1-4799-4874-12165-0608https://hdl.handle.net/11616/10222122nd IEEE Signal Processing and Communications Applications Conference (SIU) -- APR 23-25, 2014 -- Karadeniz Teknik Univ, Trabzon, TURKEYIn 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.trinfo:eu-repo/semantics/closedAccessHOGCoHOGHessian matrisTemel EgriliklerConference Object160163WOS:000356351400020N/A