Image enhancement using the local statistics

  • Ryu, Jin-Bong (Department of Visual Information Processing Korea University) ;
  • Kim, Woon-Kyung (Department of Visual Information Processing Korea University)
  • Published : 2003.11.01

Abstract

A nonlinear iterative filtering based on local statistics and anisotropic diffusion is introduced. Local statistics determines the diffusion coefficient at each iteration step. Anisotropic diffusion can be seen as estimates a piecewise smooth image from the noisy input image in the experimental section, our results are shown to suppress noise with preserving the edges. Therefore, it enhances the image and improves performance.

Keywords