Fractal Descriptors of Texture Images Based on the Triangular Prism Dimension

TL;DR

This paper introduces a new fractal-based texture descriptor using triangular prism dimensions, which improves classification and retrieval performance on standard datasets, and is robust to rotation and noise.

Contribution

The paper proposes a novel texture descriptor based on triangular prism fractal dimension and demonstrates its superior performance over existing methods.

Findings

Outperforms classical and state-of-the-art descriptors in classification and retrieval.

Effective in handling rotated textures and Gaussian noise.

Proves useful for practical texture analysis applications.

Abstract

This work presents a novel descriptor for texture images based on fractal geometry and its application to image analysis. The descriptors are provided by estimating the triangular prism fractal dimension under different scales with a weight exponential parameter, followed by dimensionality reduction using Karhunen-Lo\`{e}ve transform. The efficiency of the proposed descriptors is tested on two well-known texture data sets, that is, Brodatz and Vistex, both for classification and image retrieval. The novel method is also tested concerning invariances in situations when the textures are rotated or affected by Gaussian noise. The obtained results outperform other classical and state-of-the-art descriptors in the literature and demonstrate the power of the triangular descriptors in these tasks, suggesting their use in practical applications of image analysis based on texture features.