We present a new method which integrates fuzzy c-means cluttering and region-based level set evolution for SAR image segmentation. Benefited by spatial fuzzy clustering, the initial level set segmentation approximates the component of interest. The controlling parameters are also estimated on the basis of the results of the spatial fuzzy clustering. The proposed method was evaluated on synthetic and real SAR images, and the results show that the new method is more robust, fast, and accurate in segmentation and does not need manual intervention.%提出一种SAR图像分割方法,即整合了模糊C均值聚类和基于区域水平集演化的分割方法.该方法通过模糊聚类的结果计算水平集演化的初始化条件及控制参数,从而克服了水平集演化依赖于初始化条件和控制参数且需要较多人工干预的缺陷,增强了方法的鲁棒性.模拟图像及真实SAR图像的实验表明,该方法在不需要人工干预的情况下,能够快速、准确地分割出感兴趣区域.
展开▼