Full-reference and reduced-reference quality metrics based on SIFT

Abstract

In the last decade, an important research effort has been dedicated to implement objective image quality assessment metrics that reflect effectively human perception. Therefore, the aim of this paper is to propose new objective metrics that fulfill the demands of the image quality assessment field. For this sake, we propose two main full-reference (FR) quality metrics, and then adapt them in such a way to constitute several new reduced-reference (RR) quality metrics, for the case where the complete reference image is not available. We evaluate the influence of five types of distortion such as JPEG, JPEG2000, Gaussian Blur, AWGN, and Contrast change, on the image quality. The proposed metrics are based on the number of Scale-Invariant Feature Transform (SIFT) points, the number of SIFT matches between the unpaired and distorted images, and the Structural Similarity index (SSIM). In order to validate our proposed metrics, we compute the correlation between our metrics' scores and the subjective evaluation results. The results show a high correlation and a better quality range compared to well-known metrics, as well as a good robustness to reduced-reference situations.