Blind/Referenceless Image Spatial Quality Evaluator

Abstract

We propose a natural scene statistic based Blind/Referenceless Image Spatial QUality Evaluator (BRISQUE) which extracts the point wise statistics of local normalized luminance signals and measures image naturalness (or lack there of) based on measured deviations from a natural image model. We also model the distribution of pairwise statistics of adjacent normalized luminance signals which provides distortion orientation information. Although multi scale, the model uses easy to compute features making it computationally fast and time efficient. The frame work is shown to perform statistically better than other proposed no reference algorithms and full reference structural similarity index (SSIM).