Robust Texture Classification by Aggregating Pixel-Based LBP Statistics

Abstract

This letter addresses the texture classification problem through a pixel-based local binary pattern (LBP) statistics aggregation mechanism. Real-world texture images often present challenges for classification algorithms in terms of intra-class variability due, among others, to variable illumination. The LBP operator, a state-of-the-art texture descriptor, possesses key properties for tackling real-world texture images: discriminative power and invariance against monotonic gray level changes. We propose a novel texture classification approach that increases the robustness of LBP-based methods with respect to any type of intra-class variations. The method locally characterizes each pixel with an LBP code histogram and globally computes the label of a textured image by aggregating pixel labels through a voting process. Our approach can be in principle applied to any LBP version, as it focuses on how statistics are computed from LBP codes. We show that the proposed pixel-based approach improves upon traditional LBP block-based approaches in terms of classification accuracy by up to 5.1 p.p. on the public Outex database for the classic LBP with various neighborhoods as well as for various LBP extensions.Index Terms-Image classification, image texture, local binary pattern, pixel-based classification.

A Review of Visual Descriptors and Classification Techniques Used in Leaf Species Identification

“…In all multiscale LBPs, local information is encoded individually in each scale, but the pi-LBP can effectively encode the cross-scale correlation and provides better texture description. A pixel-based LBP was introduced in [97] instead of computing global information built on a block-based LBP the authors computed LBP based on center pixel of a half-size window which determines how much local and global information is included in the texture descriptor. It produces powerful relations for the intra-class variability of textures.…”