IMPROVING THE PERFORMANCE OF NO-REFERENCE IMAGE QUALITY ASSESSMENT ALGORITHM FOR CONTRAST-DISTORTED IMAGES USING NATURAL SCENE STATISTICS

This study was made to explore the role of two color feature in improving the performance of the existing No-Reference Image Quality Assessment Algorithm for Contrast-Distorted Images (NR-IQA-CDI). The color features used were Colorfulness and Naturalness of color expressed in CIELab and CIELuv color spaces. Test images used were the public benchmark databases that contains contrast distorted images - TID2013, CID2013 and CSIQ. Experiments for the exploration were conducted in two stages: the preliminary and the comprehensive stages. The results of preliminary study showed that the features of colorfulness and naturalness can improve the prediction of human opinion which relies mainly on the feature of brightness-only contrast. The results inspired to more comprehensive study where the Natural Scene Statistics (NSS) of the feature of these two features were estimated by modelling the probability distribution function (pdf) of the colorfulness of 16,873 test images from a public database called SUN2012.

Abstract licence: CC BY

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.