对噪声图像提出了一种改进的模糊聚类分割算法。因为模糊C均值聚类(FCM)算法具有对噪声数据敏感的缺点，该算法通过提升意义更趋明晰的模糊隶属度来改变模糊聚类中的目标函数，即通过在标准的FCM算法中使用到类的Voronoi cell的距离来取代到类的原型的欧氏距离，从而增强了聚类结果的鲁棒性。实验结果表明,改进的算法较之于FCM对于噪声图像的分割有更好的鲁棒性。

In this paper, an improved fuzzy clustering based segmentation algorithm for noise images is presented. Being sensitive to noise is one of the popular fuzzy C means (FCM) algorithm’〖KG-*3〗s drawbacks. The new objective function used in fuzzy clustering is modified to obtain different membership functions by rewarding crisp membership degrees, that is, using distances to the Voronoi cell instead of using distances to the cluster prototypes. Thus the proposed algorithm enhances robustness to noise. Experimental segmentation results for noise images demonstrate the effectiveness and robustness capability of the proposed algorithm.