三种聚类算法在建筑图像分割上的应用  

Application of Three Kinds of Clustering Algorithm in Building Image Segmentation

作　　者：周婷婷[1] 张虹波[1] 潘丽静[1] ZHOU Ting-ting ZHANG Hong-bo PAN Li-jing(School of Physics and Electronic-Electrical Engineering, Ningxia University, Yinchuan 750021)

机构地区：[1]宁夏大学物理与电子电气工程学院,银川750021

出　　处：《现代计算机（中旬刊）》2017年第1期76-80,共5页Modern Computer

摘　　要：对三种聚类算法(MeanShift、K-Means、FCM)的原理进行简单的阐述,针对Berkeley分割数据集和基准500(BSDS500)标准图片库中的一张建筑物图片在MATLAB2013a上编程实现对该图片的彩色聚类分割和灰度聚类分割,根据实验结果对三种聚类算法从参数设置、分割效果和分割时间上进行对比分析它们的优缺点,并得出结论。Describes the principle of the three clustering algorithms（Mean Shift, K-Means, FCM）. The color clustering segmentation and gray cluster-ing segmentation of a building image in the Berkeley Segmentation Dataset and Benchmark500（BSDS500） picture library are programmed and implemented in MATLAB 2013 a. According to the experimental results, compares and analyzes the advantages and disadvantages of the three clustering algorithms from the parameter setting, segmentation effect and segmentation time. Finally, draws the conclusion.

关 键 词：聚类算法 MEANSHIFT K-MEANS FCM 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]