Image Quality Assessment: A Reduced Reference Algorithm for the Super-resolution Reconstruction Image

Abstract

The previous image quality assessment(IQA) methods request the same size of original and distorted image, not suitable for the super-resolution image. The effective of image size change has rarely been discussed. An improved reduced-reference image quality assessment (RRIQA) method based on the structural similarity image metric(SSIM) and scale invariant feature transform(SIFT) was put forward. The method is applicable to the super-resolution image, and considering more than one reference image. Experimental comparisons demonstrate the effectiveness of the proposed method.