Impulse-Noise Resistant Color-Texture Classification Approach Using Hybrid Color Local Binary Patterns and Kullback–Leibler Divergence
Shervan Fekri-Ershad, Farshad Tajeripour · The Computer Journal · 2017
Texture classification is an active topic in image processing that can play an important role in many applications such as image retrieval, inspection systems, face recognition and medical image processing. There are many approaches extracting texture features in gray-level images such as local binary patterns (LBP). LBP is a nonparametric operator, which describes the local spatial structure and the local contrast of an image. One of the challenges is how to combine LBP features with color representations. Impulse noise sensitivity is another big limitation of the LBP. The use of color-texture features jointly is an efficient approach for texture classification in colored images. In this paper, an approach is proposed that consists of two phases. First, an impulse-noise resistant version of LBP is proposed, which extracts jointly color-texture features. Second, classification is evaluated based on Kullback–Leibler divergence ratio to achieve highest accuracy. The proposed approach is evaluated using Vistex, Outex, KTH-TIPS-2a data sets. Our approach has been compared with some state-of-the-art methods. It is experimentally demonstrated that the proposed approach achieves the highest accuracy. Computational complexity is computed based on the number of required operations. Low computational complexity, rotation invariant, low impulse-noise sensitivity and high usability are advantages of the proposed approach.