Image classification with binary gradient contours

Antonio Fernández

doi:10.1016/j.optlaseng.2011.05.003

Image classification with binary gradient contours

2011-09-01

51

PRE

AI

DOI：10.1016/j.optlaseng.2011.05.003

Original

Original request for help

Save

Abstract

En 中文

In this work we present a new family of computationally simple texture descriptors, referred to as binary gradient contours (BGC). The BGC methodology relies on computing a set of eight binary gradients between pairs of pixels all along a closed path around the central pixel of a 3 x 3 grayscale image patch. We developed three different versions of BGC features, namely single-loop, double-loop and triple-loop. To quantitatively assess the effectiveness of the proposed approach we performed an ensemble of texture classification experiments over 10 different datasets. The obtained results make it apparent that the single-loop version is the best performer of the BGC family. Experiments also show that the single-loop BGC texture operator outperforms the well-known LBP. Statistical significance of the achieved accuracy improvement has been demonstrated through the Wilkoxon signed rank test. (C) 2011 Elsevier Ltd. All rights reserved.

Keywords:

Texture features

BGC

LBP

Image classification with binary gradient contours

Abstract

Journal

Organization