Image and Video Quality Assessment Based on the Similarity of Edge Projections

The goal of image or video quality assessment is toevaluate if a distorted image or video is of a goodquality by quantifying the difference between the original and distorted images or videos. In this paper, toassess the visual quality of an arbitrary distortedimage or a compressed video, visual features of the imageor video are compared with those of the original image or video instead of direct comparison of two imagesor videos. As visual features, we use directional edge projections that are simply obtained by projectingvertical and horizontal edges detected by verticaland horizontal Sobel masks, respectively. Then, toassessthe image or video quality, edge projections are compared using the similarity measures of one-dimensionalhistograms such as the histogram difference, histogram intersection, Kullback-Leibler divergence,χ-squaretest, and Bhattacharyya distance. Experimental results using LIVE data set and 140 video clips that arecompressed with H.263 and H.264/AVC show the effectiveness of the proposed methods through thecomparison with conventional algorithms such as thepeak signal-to-noise ratio (PSNR), structuralsimilarity, mean singular value decomposition, andedge PSNR (EPSNR) methods.