Image denoising by anisotropic diffusion with inter-scale information fusion

Abstract

Anisotropic partial differential equations (PDEs) based schemes for denoising digital images are fast becoming an indispensable tool in computer vision problems. In this paper we propose to denoise noisy images via such multiscale anisotropic diffusion. In general, digital images contain objects of multiple scales and denoising them without destroying edges is one of the main objective in early computer vision problems. Unlike the previous approaches, which discard the multiple scale based images produced by anisotropic PDE, we utilize information contained in them. By effectively combining the inter-scale details, the proposed scheme improves upon the noise removal and detail preservation properties over other schemes. Numerical results indicate that the scheme achieves good denoising with edge preservation on a variety of images.