Adaptive center pixel selection strategy in Local Binary Pattern for texture classification

Abstract

Local Binary Pattern (LBP) is widely used in texture classification because of its powerful capability to extract texture features of a center pixel. However, LBP has three main drawbacks: (1) limited by the low resolution of imaging device, the quality of texture image is degraded, and some real existing pixels with more texture information are unavoidably lost. (2) Center pixel gc is the most important factor to extract correct LBP pattern. However, by far LBP and its variants do not show any solutions to enhance the robustness of center pixel gc. (3) Some LBP patterns include important texture microstructures, but they are ignored by uniform patterns. At the same time, some uniform patterns can be corrupted by noise and misclassified into non-uniform patterns. These LBP patterns therefore all lost their discrimination capability. In order to overcome these three disadvantages, in this paper, we propose a novel adaptive center pixel selection (ACPS) strategy.Inspired by image super-resolution techniques, ACPS firstly applies the interpolation method to recover the lost real existing pixels and generate the center pixel candidates with more texture information. Then, the gradient information is used to obtain the edge image aiming to find the non-uniform patterns at edge points which may contain complicated texture microstructures. After generating the center pixel candidates and edge image, we introduce ACPS strategy into the LBP framework. By adaptively selecting the optimal center pixel from all center pixel candidates, one non-uniform pattern at the edge point can be possibly recovered to the uniform pattern, and regain its discrimination power. It is worth noting that any other LBP variants can also employ the ACPS strategy to more effectively extract its texture features. By observing the experimental results on representative texture databases of Outex, UIUC, CUReT, XU_HR, ALOT and KTHTIPS2b after introducing the ACPS strategy into LBP and its variants of LTP, CLBP, BRINT, CRDP, FbLBP, and CJLBP, the texture classification performances can be significantly improved.