A new reduced-reference image quality assessment based on the SVD signal projection

A new image quality metric is proposed in this paper based on the degradation of structural information. It uses the singular value decomposition (SVD) as a structural projection tool called SVD-based reduced-reference image quality evaluator (SBR-IQE). This method employs the SVD signal projection to factorize the reference image matrix as well as its distorted version into their components including singular vectors and values. The singular vectors contain structural information and singular values determine the importance of each singular vector in the image structure. Thus, the minutiae perceptual information could be eliminated by singular values diagnosis. The remaining components are considered as the image features. The task of similarity measurement includes three comparisons based on luminance, contrast and structure. The overall quality evaluation is obtained according to these three comparisons. Experimental results have demonstrated that the proposed metric outperforms the state-of-the-art RR-IQA metrics and enjoys lower computational cost as well.