Energy cut based SAR image segmentation}{Energy cut based SAR image segmentation
Xiaobin Li · Scientia Sinica Informationis · 2016
This paper presents a novel graph partitioning criterion, energy cut, for SAR image segmentation, based on the law of universal gravitation. The main characteristic of the energy cut is that its optimization can produce graph partitioning with minimal inter-cluster and maximal intra-cluster gravitation. We show that the optimal continuous approximation solution to the energy cut can be obtained by solving an eigenvector problem. Furthermore, we also present a simple discretization method to derive the optimal discrete approximation solution. The experimental results on the synthesized and real-world SAR images are very encouraging, demonstrating the effectiveness of the new criterion.