Improvement of Objective Image Quality Evaluation Applying Colour Differences in the CIELAB Colour Space

Objective full-reference image quality algorithms are often designed considering the luminancecomponent of images. In this work perceived colour distance is employed in a simple andfunctional way in order to improve these full-reference image quality algorithms. The differencebetween colours in the CIELAB colour space is employed as perceived colour distance. Thisquantity is used to process images that are to be feed to full-reference image quality algorithms.This image processing stage consists of identifying the image regions or pixels that are expectedto be perceived identically by a human observer in both the reference image and the imagehaving its quality evaluated. In order to verify the validity of the proposal, objective scores arecompared with subjective ones for public available image databases. Despite being a very simplestrategy, the proposed approach was effective to improve the agreement between subjective andthe SSIM (Structural Similarity Index Metric) objective score.