Region-Level SAR Image Segmentation Based on Edge Feature and Label Assistance

This article proposes a novel segmentation algorithm for synthetic aperture radar (SAR) images. The algorithm performs region-level segmentation based on edge feature and label assistance. It demonstrates improved performance in terms of segmentation accuracy while better preserving image edges. First, an edge detection scheme is implemented, which fuses information from two advanced edge detection methods, thereby obtaining a more precise edge strength map (ESM). Second, a Canny algorithm is performed to divide the SAR image into edge regions and homogeneous regions, and different smoothing templates are selected according to pixel positions. Therefore, an anisotropic smoothing on the SAR image can be achieved, aiming at suppressing the noise within targets while also accurately maintaining the target boundaries. Third, the K-means clustering is applied to the smoothed result to generate an initial set of labels. Using ESM and the initial labels as inputs, a watershed transformation and a majority voting strategy are employed to realize an initial segmentation at the region level. Finally, a label-aided region merging (LaRM) strategy is used to correctly segment the wrongly labeled regions to give the final segmentation result. The LaRM, with merging rules based on the label rather than gray characteristics, can avoid the need for calculating a large number of complex formulas, thus accelerating the region merging. Results are presented of experiments on both simulated and real SAR images, in which the proposed region-level SAR image segmentation algorithm based on edge feature and label assistance (REFLA) method is compared against six state-of-the-art algorithms from the literature. REFLA achieves higher accuracy while better retaining the image edges.