LNPSS: SAR image despeckling based on local and non-local features using patch shape selection and edges linking

Abstract Removal of speckle noise from Real SAR images is a significant task for the better segmentation, target detection, target recognition or other processing. In this paper, a novel complex strategy is presented based on carefully analyzing the effect of the speckle noise on the histogram. The histogram of a patch is expanded in the image corrupted with speckle noise. To overcome this, we introduced some rules to remove both noise and preserve the crucial features (edges). Owing to the use of patch shape selection automatically, the patch's histogram modification is more effective. Our method, also, is being able to reconstruct some missing edges by using the kirsch filter and edge linking approach. Our satisfactory results indicate that the proposed approach has a competitive despeckling performance in terms of both visual quality assessment and preserving vital details.