LAUSR

Based on the key observation that the coding residuals between the recovered sparse codes of the noisy SAR image and those of the clean SAR image are sparse, we propose a sparse representation-based despeckling algorithm for SAR image. As the sparse codes of the clean SAR image are not available, the rich nonlocal repetitive structures of the logarithmic SAR images are exploited. To collect the similar patches within the logarithmic SAR image, an adaptive similarity evaluation obeying statistical distribution of the logarithmic speckle noise is derived. Experimental results on both synthetic and real SAR images demonstrate the validity of the proposed algorithm.