Abstract: Fuzzy C-means（FCM） clustering algorithm has been widely used in image segmentation.Because of the heavy computing burden of the Fuzzy C-Means clustering and the disadvantage that clustering performance is affected by initial centers of FCM.This paper proposes a method of Fuzzy C-means Clustering based on Particle Swarm Optimization algorithm for image segmentation.As the search is based on density of the cluster center，the computational load is small，thus，the computing speed of FCM can be improved.Experimental results show that this method can make a marked improvement in the speed of fuzzy clustering and can segment the image quickly and effectively．

Key words: fuzzy c-means cluster, color image segmentation, clustering center, particle swarm optimization algorithm, robust

摘要： 模糊C-均值聚类算法广泛用于图像分割，但存在聚类性能受类中心初始化影响，且计算量大等问题。为此，提出了一种基于微粒群的模糊C-均值聚类图像分割算法，该方法利用微粒群较强的搜索能力搜索聚类中心。由于搜索聚类中心是按密度进行，计算量小，故可以大幅提高模糊C-均值算法的计算速度。实验表明，这种方法可以使模糊聚类的速度得到明显提高，实现图像的快速分割。

关键词: 模糊C-均值聚类, 彩色图像分割, 聚类中心, 微粒群优化算法, 鲁棒性