Sparsity Based No-Reference Image Quality Assessment for Automatic Denoising

In image and video denoising, a quantitative measure of genuine image content, noise, and blur is required to facilitate quality assessment, when the ground-truth is not available. In this paper, we present a no-reference image quality assessment for denoising applications, that examines local image structure using orientation dominancy and patch sparsity. We propose a fast method to find the dominant orientation of image patches, which is used to decompose them into singular values. Combining singular values with the sparsity of the patch in the transform domain, we measure the possible image content and noise of the patches and of the whole image. To measure the effect of noise accurately, our method takes both low and high textured patches into account. Before analyzing the patches, we apply a shrinkage in transform domain to increase the contrast of genuine image structure. We show that the proposed method is useful to select parameters of denoising algorithms automatically in different noise scenarios such as white Gaussian and processed noise. Our objective and subjective results confirm the correspondence between the measured quality and the ground-truth. We show that the proposed method rivals related state-of-the-art no-reference quality assessment approaches.