A Study of the Perceptually Weighted Peak Signal-To-Noise Ratio (WPSNR) for Image Compression

The peak signal-to-noise ratio (PSNR) is the most used objective measure for assessing perceptual image quality when it comes to image and video compression tasks, despite the fact that it exhibits weak performance in reflecting human perception. To address this problem, many image quality assessment (IQA) methods were proposed, e. g. the structural similarity quality measure (SSIM) and its extension, the multi-scale SSIM (MS-SSIM). In this paper we revisit and evaluate a block-based perceptually weighted PSNR (WPSNR) which calculates weighting factors to capture visual sensitivity of local image regions. We further introduce a sample-based version of WPSNR which determines those sensitivity weights with higher spatial accuracy. These methods are computationally inexpensive compared to other similarity measures and are shown to outperform PSNR, SSIM and similar perceptual quality measures when it comes to approximate subjective ratings of JPEG or JPEG2000 compressed images.