图像分割的快速模糊c均值聚类算法  

A Fast Fuzzy C-Means Clustering Algorithm for Image Segmentation

作　　者：周礼平[1] 高新波[1] 

机构地区：[1]西安电子科技大学电子工程学院,西安710071

出　　处：《计算机工程与应用》2004年第8期68-70,共3页Computer Engineering and Applications

摘　　要：提出了一种快速有效的图像模糊c-均值(FCM)聚类分割方法。该方法一方面通过特征映射减少数据量,另一方面通过调整算法的计算步骤以减少迭代过程的存储量,从而大大缩短图像分割的运行时间。应用于图像分割的实验结果表明新算法在保持原有FCM分割效果的同时大大缩短了CPU时间。A fast and efficient algorithm of FCM clustering(FFCM)algorithm is proposed for image segmentation.In the one hand,the novel algorithm reduces the data amount by feature space mapping;in the other hand,it modifies the computing steps to lessen storage space of the operation data.The above two steps improve the efficiency of the fuzzy clustering algorithm.The experimental results with real image segmentation illustrate that the new FFCM algorithm greatly decreases the CPU time with keeping the same segmentation performance with traditional FCM based segmentation algo-rithm.

关 键 词：模糊C-均值聚类 图像分割 特征映射 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]