Binary Distance Transform to Improve Feature Extraction

TL;DR

This paper introduces a binary distance transform technique applied to texture images to enhance feature extraction and improve recognition accuracy, especially under challenging conditions like noise and illumination variations.

Contribution

The paper presents a novel application of binary distance transform on texture datasets, significantly improving recognition performance over traditional methods.

Findings

Up to 10% accuracy improvement on Outex dataset

Effective in handling noise, scale, and illumination artefacts

Outperforms traditional feature extraction approaches

Abstract

To recognize textures many methods have been developed along the years. However, texture datasets may be hard to be classified due to artefacts such as a variety of scale, illumination and noise. This paper proposes the application of binary distance transform on the original dataset to add information to texture representation and consequently improve recognition. Texture images, usually in grayscale, suffers a binarization prior to distance transform and one of the resulted images are combined with original texture to improve the amount of information. Four datasets are used to evaluate our approach. For Outex dataset, for instance, the proposal outperforms all rates, improvements of an up to 10\%, compared to traditional approach where descriptors are applied on the original dataset, showing the importance of this approach.