|
Restoring image quality through structure preserving de-noising Prakash Ishwar, Krishna Ratakonda , Pierre Moulin and Narendra Ahuja In many image transmission and acquisition situations, the image may become corrupted by additive noise. De-noising refers to the process of removing the noise while maintaining good visual quality. This problem has assumed major significance with the increase in image related communication that has accompanied the exponential growth of the internet. Traditionally, image quality is measured in terms of PSNR (Peak Signal to Noise Ratio) which may have limited relation, at best, to the perceptual quality of the image. In this paper we present a novel de-noising scheme which results in significantly improved performance in terms of both perceptual quality and PSNR. Furthermore, we show that the de-noising framework that we propose encompasses the usual linear transform based de-noising schemes as special cases. Keywords: image denoising; multiple compaction
domains; signal denoising; compact |