Reorganizing local image features with chaotic maps: an application to texture recognition

TL;DR

This paper introduces a chaos-based local descriptor for texture recognition that leverages chaotic maps to reorganize image features, demonstrating competitive results on benchmark and biological datasets.

Contribution

It proposes a novel chaos-inspired method for texture analysis that enhances feature representation without relying on large training datasets.

Findings

Achieved competitive accuracy on benchmark texture datasets.

Successfully identified Brazilian plant species based on leaf surface textures.

Outperformed some modern learning-based approaches in texture classification.

Abstract

Despite the recent success of convolutional neural networks in texture recognition, model-based descriptors are still competitive, especially when we do not have access to large amounts of annotated data for training and the interpretation of the model is an important issue. Among the model-based approaches, fractal geometry has been one of the most popular, especially in biological applications. Nevertheless, fractals are part of a much broader family of models, which are the non-linear operators, studied in chaos theory. In this context, we propose here a chaos-based local descriptor for texture recognition. More specifically, we map the image into the three-dimensional Euclidean space, iterate a chaotic map over this three-dimensional structure and convert it back to the original image. From such chaos-transformed image at each iteration we collect local descriptors (here we use local binary patters) and those descriptors compose the feature representation of the texture. The performance of our method was verified on the classification of benchmark databases and in the identification of Brazilian plant species based on the texture of the leaf surface. The achieved results confirmed our expectation of a competitive performance, even when compared with some learning-based modern approaches in the literature.