Full-reference image quality assessment scheme based on deformed pixel and gradient similarity

Image quality assessment (IQA) is important for numerous image processing measures, such as reproduction, restoration, enhancement,- compression and acquisition. In this paper, a full -reference scheme for image quality assessment is proposed, which supplies more flexibility than previous methods in using edge similarity and distorted pixel measure. First, test and reference images are transformed using distorted pixel measure. And second, we calculate the difference between the two images, which can be used to compute the whole error. Experimental comparisons demonstrate the effectiveness of the proposed method. (C) 2015 Elsevier GmbH. All rights reserved.