Image Denoising based on Visual Patterns

Among abundant image denoising methods proposed so far, the use of patch based algorithms have attracted a lot of attention from image processing community. Although these methods are very powerful in presentation of high quality results, the impact of human visual system (HVS) is ignored in sole of them. In this paper the human visual geometry is used in preparation of a new method for image denoising. Several image quality assessment (IQA) criteria, based on HVS, are used to confirm superiority of the proposed method in comparison with other state-of-the-art methods. In addition to denoising quality, the proposed method is fast as a result of dimensionality reduction.