基于微粒群优化的模糊C-均值聚类图像分割  

Fuzzy C-means clustering based on particle swarm optimization algorithm for image segmentation

作　　者：黄力明[1] 

机构地区：[1]镇江高等专科学校电子信息系,江苏镇江212003

出　　处：《计算机工程与设计》2008年第9期2300-2303,共4页Computer Engineering and Design

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。实验结果表明,该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。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. A method of Fuzzy C-means clustering based on particle swarm optimization algorithm for image segmentation is proposed. As the search is based on density of the cluster center, the computational load is small, thus, the computing speed of FCM is 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.

关 键 词：模糊C-均值聚类 图像分割 聚类中心 微粒群优化算法 鲁棒性 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]