Blind quality assessment of JPEG2000 compressed images using natural scene statistics

Measurement of image quality is crucial for many image-processing algorithms, such as acquisition, compression, restoration, enhancement and reproduction. Traditionally, researchers in image quality assessment have focused on equating image quality with similarity to a ´reference´ or ´perfect´ image. The field of blind, or no-reference, quality assessment, in which image quality is predicted without the reference image, has been largely unexplored. In this paper, we present a blind quality assessment algorithm for images compressed by JPEG2000 using natural scene statistics (NSS) modelling. We show how reasonably comprehensive NSS models can help us in making blind, but accurate, predictions of quality. Our algorithm performs close to the limit imposed on useful prediction by the variability between human subjects.