Color image quality assessment measure using multivariate generalized Gaussian distribution

TL;DR

This paper introduces a new color image quality assessment method using multivariate generalized Gaussian distribution to model RGB correlations, providing effective quality evaluation with minimal original image data.

Contribution

It models RGB correlations with MGGD and uses KLD for quality assessment, offering a novel reduced-reference approach for diverse distortions.

Findings

Effective across various distortion types

Uses minimal original image information

Outperforms existing methods on TID 2008 benchmark

Abstract

This paper deals with color image quality assessment in the reduced-reference framework based on natural scenes statistics. In this context, we propose to model the statistics of the steerable pyramid coefficients by a Multivariate Generalized Gaussian distribution (MGGD). This model allows taking into account the high correlation between the components of the RGB color space. For each selected scale and orientation, we extract a parameter matrix from the three color components subbands. In order to quantify the visual degradation, we use a closed-form of Kullback-Leibler Divergence (KLD) between two MGGDs. Using "TID 2008" benchmark, the proposed measure has been compared with the most influential methods according to the FRTV1 VQEG framework. Results demonstrates its effectiveness for a great variety of distortion type. Among other benefits this measure uses only very little information about the original image.