一种基于模糊聚类的快速图像分割算法  

A fast image segmentation algorithm based on fuzzy clustering

作　　者：杨润玲[1] 高新波[2] 介军[1] 

机构地区：[1]西安建筑科技大学信控学院,陕西西安710055 [2]西安电子科技大学电子工程学院,陕西西安710071

出　　处：《西安建筑科技大学学报（自然科学版）》2007年第2期280-285,共6页Journal of Xi'an University of Architecture & Technology(Natural Science Edition)

基　　金：国家自然科学基金资助项目(60202004);教育部重点项目(104173)

摘　　要：提出一种基于二维直方图加权的模糊c均值图像快速分割算法.通过将原图像和它的平滑图像相结合,构造一个二元组的“广义图像”,广义图像的直方图就是原图像的二维直方图.然后对此二维直方图进行塔形分解得到金字塔的上一层——顶层,相应地称原二维直方图为底层.最后,利用加权模糊c均值聚类算法分别对顶层和底层进行模糊聚类,从而实现对原图像的分割.实验结果与性能分析表明,该算法具有较高的分割速度和良好的抑制噪声的能力.This paper studies the application of fuzzy c-means （FCM） clustering algorithm in the image segmentation, and a fast image segmentation method is presented based on a 2D histogram weighting FCM algorithm. Firstly, by combining original image and its smooth image, a generalized image is constructed. Secondly, the 2D histogram is decomposed into a pyramid structure with 2 layers（one upper and one lower）. Finally, the weighting FCM algorithm is performed on the two layers respectively to implement the original image segmentation. The experimental results illustrate that the pro- posed algorithm can implement image segmentation quickly and suppress the noise effectively.

关 键 词：图像分割 加权模糊c均值聚类算法 塔形结构 二维直方图 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]