【摘要】 传统的单一模糊聚类算法(FCM)适用于无噪声图像的分割,而对于具有噪声、特殊点值及瑕疵的图像分割则无能为力。本文提出了应用嵌入空间信息的模糊聚类算法(SFCM)与水平集方法的结合,对海洋溢油污染的合成孔径雷达(SAR)图像进行分割处理,得到了优于其它算法的分割图像。通过对SAR溢油图像分割的数据分析,验证了算法的有效性。更多还原

【Abstract】 In this paper a robust method for oil spill SAR image segmentation is explored.The unique FCM algorithm yields better results for segmenting noise free images,but it fails to segment images degraded by noise,outliers and other imaging defects,an integrated method of spatial based FCM(SFCM) and level set method for oil spill segmentation is discussed.By analysing segmentation of Oil spill SAR image,it verify the effectiveness of the algorithm.更多还原