An Effective Segmentation Algorithm for MSTAR SAR Target Chips

We present an effective segmentation algorithm for MSTAR SAR target chips. First, the image over-segmentation is implemented to acquire image regions. Then the region-level and pixel-level features are generated to represent SAR images of MSTAR SAR chips. Finally, the Graph-Cut and Branch-and-Bound algorithms are applied to the energy function obtained by sLDA and MRF to achieve the final segmentation results. Through a comparison of distinct SAR image segmentation experiments, our simulation results demonstrate the superior performance of our proposed method in terms of effectiveness.