On color image quality assessment using natural image statistics

TL;DR

This paper extends existing image quality assessment methods to color images by exploring RGB and CIELAB color spaces, demonstrating that CIELAB significantly improves assessment accuracy for various distortions.

Contribution

It introduces a color image quality assessment approach based on natural image statistics, highlighting the effectiveness of CIELAB over RGB in this context.

Findings

CIELAB improves quality assessment accuracy for many distortions

Color information enhances the performance of image quality measures

Extensive evaluation on TID 2013 benchmark supports these findings

Abstract

Color distortion can introduce a significant damage in visual quality perception, however, most of existing reduced-reference quality measures are designed for grayscale images. In this paper, we consider a basic extension of well-known image-statistics based quality assessment measures to color images. In order to evaluate the impact of color information on the measures efficiency, two color spaces are investigated: RGB and CIELAB. Results of an extensive evaluation using TID 2013 benchmark demonstrates that significant improvement can be achieved for a great number of distortion type when the CIELAB color representation is used.