General-purpose reduced-reference image quality assessment based on perceptually and statistically motivated image representation

Divisive normalization has been recognized as a successful approach to model the perceptual sensitivity of biological vision. It also provides a useful image representation that is well-matched to the statistical properties of natural images. Here we propose a reduced- reference image quality assessment method in the divisive normalization transform domain, where the quality of an image is evaluated based on a set of reduced-reference features extracted from a divisive normalization representation of the image. The proposed method is general-purpose, in the sense that no assumption is made about the types of distortions occurred in the image being evaluated. The proposed method is trained and tested using the LIVE database and demonstrates good performance for a wide range of distortions.