An information-theoretic wavelet-based texture descriptor using Gaussian Markov random field models

Texture characterization and identification is a key issue for a variety of computer vision and image processing applications. Current techniques developed for dealing with the purpose thereof still present performance issues when applied in the presence of noise, owing to the intrinsic properties of the image being analyzed can not be maintained. Based on the principle that data distribution of these textures form a non-deterministic complex system, mathematical tools can help to characterize them. In this paper, we propose new approaches capable of quantifying such intrinsic properties by means of the Fisher information matrix. The methodology consists in firstly defining each wavelet sub-band of the texture image as a complex system modeled by a Gaussian Markov Random Field and secondly computing their respective Fisher information matrix and Shannon entropy. Applying the proposed texture descriptor to Salzburg and Outex datasets revealed a significant superiority of the proposed method vis-a-vis the majority of traditional and novel texture descriptors presented in the literature.