基于改进模糊均值聚类算法的遥感图像聚类

Remote Sensing Image Clustering Based on Modified FCM Clustering Algorithm

由于传统模糊C均值聚类算法存在缺陷,该文给出了一种结合加权模糊C均值聚类与聚类有效性指数的算法。利用数据点的密度大小作为权值,借助数据本身的分布特性,该方法不仅在一定程度上克服了模糊均值算法的缺陷——有对数据集进行等划分的趋势,而且具有良好的收敛性。

As the fuzzy C-means clustering algorithm（FCM） has shortcomings. To solve the above problem, this paper proposes a combination of WFCM algorithm and cluster validity index. Distributing density size of data dot is regard as weighted value, in virtue of distributing characteristic of data＇s own, the method has not only to certain extent overcome limitation of fuzzy C-means algorithm--having limitation of equal partition trend for data sets, but also been favorable convergence.