Centroid-based texture classification using the SIRV representation

Abstract

This paper introduces a centroid-based (CB) supervised classification algorithm of textured images. In the context of scale/orientation decomposition, we demonstrate the possibility to develop centroid approach based on multivariate stochastic modeling. The main interest of the multivariate modeling comparatively to the univariate case is to consider spatial dependency as additional features for characterizing texture content. The aim of this paper is twofold. Firstly, we introduce the Spherically Invariant Random Vector (SIRV) representation for the modeling of wavelet coefficients. Secondly, from the specific properties of the SIRV process, i.e. the independence between the two sub-processes of the compound model, we derive centroid estimation scheme. Experiments from various conventional texture databases are conducted and demonstrate the interest of the proposed classification algorithm.

Computing the Kullback-Leibler Divergence between two Generalized Gamma Distributions

“…As a flexible skewed distribution, the generalized gamma is frequently used for life-time analysis and reliability testing. In addition, it models fading phenomena in wireless communication, has been applied in automatic image retrieval and analysis [4,5,6], was used to evaluate dimensionality reduction techniques [7], and also appears to be connected to diffusion processes in (social) networks [8,9,10]. Accordingly, methods for measuring (dis)similarities between generalized gamma distributions are of practical interest in data science because they facilitate model selection and statistical inference.…”

Intrinsic prior for Bayesian classification of texture images

“…By exploiting the independence of the processes τ and g and by working on the joint vector y = (τ, g), the Jeffrey divergence of the joint model can be expressed as the sum of the Jeffrey divergence for the multivariate Gaussian process and the Jeffrey divergence for the multiplier part. Note that both terms admit a closed-form expression recalled in [17]. It yields that the centroid for a SIRV model y is composed by two centroids: one for the Gaussian part and one for the multiplier part.…”

“…It yields that the centroid for a SIRV model y is composed by two centroids: one for the Gaussian part and one for the multiplier part. For more information dealing with the implementation of those centroids estimators, the interested reader is referred to [17].…”

Comparing a complex-valued sinusoidal process with an autoregressive process using Jeffrey's divergence

“…For this purpose, we propose to use the Jeffrey's divergence (JD) which is the symmetric version of the Kullback-Leibler (KL) divergence. Both divergences have been used in a wide range of applications, starting from biomedical applications [6], passing through radar clutter analysis [7] and model motion comparison [8], to texture analysis [9] [10]. They consist in comparing probability density functions (pdf).…”