Multiresolution gray-scale and rotation invariant texture classification with local binary patterns

TLDR

The method is based on recognizing that certain local binary patterns, termed “uniform,” are fundamental properties of local image texture and their occurrence histogram is a powerful texture feature. The study proposes a simple, efficient multiresolution approach for gray‑scale and rotation‑invariant texture classification using local binary patterns and nonparametric discrimination of sample and prototype distributions. The method derives a generalized gray‑scale and rotation‑invariant operator that detects uniform patterns at any angular quantization and spatial resolution, and combines multiple operators for multiresolution analysis. The approach is robust to gray‑scale variations, computationally simple, and experimental results demonstrate strong discrimination using simple rotation‑invariant local binary pattern statistics.

Abstract

Presents a theoretically very simple, yet efficient, multiresolution approach to gray-scale and rotation invariant texture classification based on local binary patterns and nonparametric discrimination of sample and prototype distributions. The method is based on recognizing that certain local binary patterns, termed "uniform," are fundamental properties of local image texture and their occurrence histogram is proven to be a very powerful texture feature. We derive a generalized gray-scale and rotation invariant operator presentation that allows for detecting the "uniform" patterns for any quantization of the angular space and for any spatial resolution and presents a method for combining multiple operators for multiresolution analysis. The proposed approach is very robust in terms of gray-scale variations since the operator is, by definition, invariant against any monotonic transformation of the gray scale. Another advantage is computational simplicity as the operator can be realized with a few operations in a small neighborhood and a lookup table. Experimental results demonstrate that good discrimination can be achieved with the occurrence statistics of simple rotation invariant local binary patterns.