Image processing using diffusion processes

We propose a new algorithm inspired by the properties of diffusion processes for image filtering. We show that purely nonlinear diffusion process ruled by Fisher equation allows contrast enhancement and noise filtering, but involves a blurry image. By contrast, anisotropic diffusion, described by Perona and Malik algorithm, allows noise filtering and preserves the edges. We show that combining the properties of anisotropic diffusion with those of nonlinear diffusion provides a better processing tool which enables noise filtering, contrast enhancement and edge preserving. We trust that this algorithm could be electronically implemented.