Multilayer Complex Network Descriptors for Color-Texture Characterization

TL;DR

This paper introduces a novel multilayer complex network approach for color-texture analysis, modeling images as networks per color channel, and demonstrates superior classification performance over existing methods including deep learning.

Contribution

It proposes a new multilayer complex network model for color-texture characterization with adaptive thresholding and demonstrates its effectiveness through extensive classification experiments.

Findings

Achieved 97.7% mean accuracy across five datasets.

Outperformed deep convolutional neural networks like ResNet.

Introduced new characterization techniques for spatial interactions.

Abstract

A new method based on complex networks is proposed for color-texture analysis. The proposal consists on modeling the image as a multilayer complex network where each color channel is a layer, and each pixel (in each color channel) is represented as a network vertex. The network dynamic evolution is accessed using a set of modeling parameters (radii and thresholds), and new characterization techniques are introduced to capt information regarding within and between color channel spatial interaction. An automatic and adaptive approach for threshold selection is also proposed. We conduct classification experiments on 5 well-known datasets: Vistex, Usptex, Outex13, CURet and MBT. Results among various literature methods are compared, including deep convolutional neural networks with pre-trained architectures. The proposed method presented the highest overall performance over the 5 datasets, with 97.7 of mean accuracy against 97.0 achieved by the ResNet convolutional neural network with 50 layers.