计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (33): 182-184.DOI: 10.3778/j.issn.1002-8331.2010.33.051

• 图形、图像、模式识别 • 上一篇    下一篇

图像分割的改进的加权模糊聚类算法

翁文田,赵曙光   

  1. 东华大学 信息科学与技术学院,上海 201620
  • 收稿日期:2009-04-01 修回日期:2009-06-01 出版日期:2010-11-21 发布日期:2010-11-21
  • 通讯作者: 翁文田

Improved weighted fuzzy clustering algorithm for image segmentation

WENG Wen-tian,ZHAO Shu-guang   

  1. College of Information Science and Technology,Donghua University,Shanghai 201620,China
  • Received:2009-04-01 Revised:2009-06-01 Online:2010-11-21 Published:2010-11-21
  • Contact: WENG Wen-tian

摘要: 利用模糊聚类算法对图像进行分割是一种比较经典的方法,但是标准的FCM算法并没有考虑像素的空间信息对聚类结果的影响。利用S函数将空间信息转为模糊聚类算法的目标函数的权值,从而使目标函数更合理。实验结果表明,改进算法较标准的FCM算法具有更好的分割效果。

关键词: 图像分割, 模糊聚类算法, S函数, 空间信息

Abstract: It is well-known to do image-segmentation using Fuzzy C-Means(FCM) clustering method,but the standard Fuzzy C-Means algorithm doesn’t take the pixel spatial information into account,which has influence on the classification result.In order to make the objective function more reasonable,this paper converts the spatial information into the weight of the objective function using the S-function.Experimental results show that the improved algorithm yields better result than the standard Fuzzy C-Means algorithm.

Key words: image segmentation, fuzzy C-means, S-function, spatial information

中图分类号: