Improving LBP and its variants using anisotropic diffusion

TL;DR

This paper introduces a preprocessing technique using anisotropic diffusion to enhance local binary pattern (LBP) features, significantly improving texture classification accuracy.

Contribution

It proposes a novel preprocessing step with anisotropic diffusion methods to improve local feature descriptors for texture recognition.

Findings

Preprocessing with anisotropic diffusion enhances texture recognition accuracy.

Combining transformed and original images yields better results.

Anisotropic diffusion outperforms Gaussian kernel in feature enhancement.

Abstract

The main purpose of this paper is to propose a new preprocessing step in order to improve local feature descriptors and texture classification. Preprocessing is implemented by using transformations which help highlight salient features that play a significant role in texture recognition. We evaluate and compare four different competing methods: three different anisotropic diffusion methods including the classical anisotropic Perona-Malik diffusion and two subsequent regularizations of it and the application of a Gaussian kernel, which is the classical multiscale approach in texture analysis. The combination of the transformed images and the original ones are analyzed. The results show that the use of the preprocessing step does lead to improved texture recognition.