Learning Local Complex Features using Randomized Neural Networks for Texture Analysis

TL;DR

This paper introduces a novel texture analysis method that models textures as directed networks and uses a randomized neural network trained on topological features for improved classification performance.

Contribution

It combines Complex Network theory with randomized neural networks to learn local texture features, offering a new approach for texture characterization.

Findings

High classification accuracy on four image databases

Effective modeling of textures as directed networks

Fast learning algorithm for local pattern extraction

Abstract

Texture is a visual attribute largely used in many problems of image analysis. Currently, many methods that use learning techniques have been proposed for texture discrimination, achieving improved performance over previous handcrafted methods. In this paper, we present a new approach that combines a learning technique and the Complex Network (CN) theory for texture analysis. This method takes advantage of the representation capacity of CN to model a texture image as a directed network and uses the topological information of vertices to train a randomized neural network. This neural network has a single hidden layer and uses a fast learning algorithm, which is able to learn local CN patterns for texture characterization. Thus, we use the weighs of the trained neural network to compose a feature vector. These feature vectors are evaluated in a classification experiment in four widely used image databases. Experimental results show a high classification performance of the proposed method when compared to other methods, indicating that our approach can be used in many image analysis problems.