Edge-region information measure based on deformed and displaced pixel for image quality assessment

Image quality depends on many factors, such as the initial capture system and its image processing, compression, transmission, the output device, media and associated viewing conditions. The goal of quality assessment research is to design measures that can automatically evaluate the quality of images in a perceptually consistent manner. This paper proposes a new measure for image quality assessment (IQA), which supplies more flexibility than previous methods in using the pixel displacement in the assessment. First, the distorted and original images are divided into overlapped 11×11 blocks, and secondly, we calculated distorted pixels and displacement, and then, visual regions of interest and edge information are computed, which can be used to compute the global error. Experimental comparisons show the efficiency of the proposed method.

► A novel measure for image quality assessment exploiting displaced pixel is proposed.
► Popular Sobel and Entropy operators are used to produce edge and visual regions.
► Deformed and displaced pixel measures are used inside the proposed method.
► Performance of ERDDM measure is compared against PSNR, MSSIM, VroiWQI and GSSIM.
► The proposed measure is robust to assess, white noise and Gaussian blur.