Spatio-spectral networks for color-texture analysis
Abstract
Texture is one of the most-studied visual attribute for image characterization since the 1960s. However, most hand-crafted descriptors are monochromatic, focusing on the gray scale images and discarding the color information. In this context, this work focus on a new method for color texture analysis considering all color channels in a more intrinsic approach. Our proposal consists of modeling color images as directed complex networks that we named Spatio-Spectral Network (SSN). Its topology includes within-channel edges that cover spatial patterns throughout individual image color channels, while between-channel edges tackle spectral properties of channel pairs in an opponent fashion. Image descriptors are obtained through a concise topological characterization of the modeled network in a multiscale approach with radially symmetric neighborhoods. Experiments with four datasets cover several aspects of color-texture analysis, and results demonstrate that SSN overcomes all the compared literature methods, including known deep convolutional networks, and also has the most stable performance between datasets, achieving of average accuracy against of MCND and of AlexNet. Additionally, an experiment verifies the performance of the methods under different color spaces, where results show that SSN also has higher performance and robustness.
Cite
@article{arxiv.1909.06446,
title = {Spatio-spectral networks for color-texture analysis},
author = {Leonardo F. S. Scabini and Lucas C. Ribas and Odemir M. Bruno},
journal= {arXiv preprint arXiv:1909.06446},
year = {2022}
}