2-d signature of images and texture classification

TL;DR

This paper introduces a 2D signature concept inspired by rough paths theory to extract low-dimensional features from images, demonstrating high accuracy in texture classification tasks.

Contribution

It proposes a novel 2D signature framework for images, providing an effective low-dimensional feature extraction method for pattern and texture classification.

Findings

Low-dimensional signature features achieve high classification accuracy.

The method is inspired by rough paths theory.

Effective for texture classification.

Abstract

We introduce a proper notion of 2-dimensional signature for images. This object is inspired by the so-called rough paths theory, and it captures many essential features of a 2-dimensional object such as an image. It thus serves as a low-dimensional feature for pattern classification. Here we implement a simple procedure for texture classification. In this context, we show that a low dimensional set of features based on signatures produces an excellent accuracy.