SAR image restoration based on the alpha-stable prior in the wavelet domain

Synthetic Aperture Radar (SAR) image is generally degraded by multiplicative Speckle. In this paper, an algorithm for SAR image restoration in the wavelet domain is presented. The Alpha-stable distribution is utilized to model the wavelet coefficients of the SAR image based on their statistic characteristics. A closed-form expression of the Bayesian filter is obtained. The experimental results indicate that the proposed algorithm has capability both in Speckle suppression and in details preservation.