Evolutionary expert-supervised despecled srad filter design for SAR images

Abstract

There is no ideal speckle reduction filtering technique to efficiently reduce the level of noise in SAR images, while considering experts validation criteria which include a subjective component. We present an interactive easy-to-use software package, based on an evolutionary algorithm to perfor adaptive anisotropic diffusion speckle filtering for SAR images. As a main difference from other methodologies, there is a implication of SAR image processing expert which provides a subjective validation to complete the diffusion filter design. We apply the methodology to a set of SAR images having speckle and the results show the excellent potential of the proposal.