Abstract:

For the problem of sequence of region merging in synthetic aperture radar (SAR) images segmentation using region merging techniques, an edgeguided region merging technique is proposed. Firstly, an improved ratio edge detection operator is used to obtain an initial partition of an original SAR image. Then, a real value function using areas of adjacent regions and edge information is designed to determine the sequence of region merging, which improves the precision of parameter estimation of a model and preserves stronger edges of the image. Finally, the proposed region merging approach is used to solve an SAR image segmentation model based on the minimum description length (MDL) principle and polygonal grid. The experiments show that, compared with similar methods, the proposed region merging algorithm improves the edge detection performance and localization precision.