A New Approach for Recognition of Mosaic Textures by LBP Based On RGB Model

The method is based on recognizing that certain local binary patterns, termed are fundamental propertiesof local image texture and their occurrence histogram is proven to be a very powerful texture feature.TheLocal Binary Pattern (LBP) is a texture descriptorbased on the probability of occurrence of elementarybinary patterns (texels) defined over a circular window. A new feature set derived from the LBP, called theLBP-Constant-Symmetry (LBP-CS) and LBP-High-Symmetry (LBP-HS) are proposed for recognition ofstone textures. The features are computed from eachband of an isotropic color LBP Matrix for recognition.The tests were conducted in a variety of industrialsamples. The obtained results are promising and showthe possibility of efficiently recognizing complexindustrial products based on color and texture featur