一种基于集合划分的鲁棒性自适应模糊聚类分割算法

模糊C均值算法(FCM)是图像分割最常用的算法之一,这种方法需要提前确定初始聚类中心和聚类数.为此,提出了一种新的自适应模糊聚类算法(AFCM),AFCM算法中构造的观察矩阵、判断矩阵和集合划分可以自动确定合适的聚类数.为了得到更好的图像分割效果,采用核距离作为相似性度量,提出了一种鲁棒性自适应模糊C均值算法(RAFCM).实验结果表明,与FCM算法相比,AFCM和RAFCM算法不仅能自动地确定聚类数目,还可以得到更好的图像分割质量.

A Robust Adaptive Fuzzy Clustering Segmentation Algorithm Based on Set Partition

Fuzzy C-means algorithm(FCM)is one of the most commonly used algorithms in image segmentation.In FCM,the initial cluster center and the number of clustering are determined in advance.To address this problem,a new adaptive fuzzy clustering algorithm(AFCM)is proposed.In AFCM algorithm,observation matrix,judgment matrix and set partitioning are used to select the appropriate clustering number automatically.In order to get better image segmentation effect,a robust adaptive fuzzy clustering algorithm(RAFCM)which using kernel distance as a similarity measure is proposed.The experimental results show that,compared with the FCM algorithm,the AFCM and RAFCM algorithms can not only determine the number of clustering automatically but also get better image segmentation quality.