Evolutionary Expert-Supervised Despeckled SRAD Filter Design for SAR Images

Inhalt:
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 perform adaptive anisotropic diffusion speckle filtering for SAR images. As a main difference from other methodologies, there is an 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.