A new algorithm for SAR image denoising based on adaptive shrinkage in Nonsubsampled Contourlet Domain

is presented . The nonsubsampled contourlet coefficients of SAR images are reduced by the corresponding Pizurica adaptive shrinkage factor. The Pizurica shrinkage factor takes into account not only the local noise measure

but also prior directional spatial consistency

and combines the shift-invariance and direction selectivity of the nonsubsampled contourlet transform. The shrinkage factor is assembled at each high frequency subband to modify the nonsubsampled contourlet coefficients. Inverse nonsubsampled contourlet transform is performed on the updated coefficients to get the denoised image. Compared with the denoising methods based on wavelet soft-threshold and contourlet soft-threshold

the proposed algorithm can reduce speckle noise more effectively while preserving the edges of the SAR images.