计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (8): 177-179.DOI: 10.3778/j.issn.1002-8331.2010.08.050

• 图形、图像、模式识别 • 上一篇    下一篇

用于图像分割的粗糙集改进模糊聚类方法

张月琴,白雅彬   

  1. 太原理工大学 计算机与软件学院,太原 030024
  • 收稿日期:2008-09-11 修回日期:2008-11-28 出版日期:2010-03-11 发布日期:2010-03-11
  • 通讯作者: 张月琴

Approach of image segmentation using fuzzy clustering based on rough-set

ZHANG Yue-qin,BAI Ya-bin   

  1. College of Computer and Software,Taiyuan University of Technology,Taiyuan 030024,China
  • Received:2008-09-11 Revised:2008-11-28 Online:2010-03-11 Published:2010-03-11
  • Contact: ZHANG Yue-qin

摘要: 采用一种新的基于粗糙集理论的图像分割算法。通过提取直方图的外层,以及计算像素点周围的局部模糊程度来更新粗糙度。使用局部模糊粗糙度和待定算子来更新FCM算法中的隶属度函数。从粗糙集理论意义上来说,直方图的外层与上近似有关,而直方图取值与下近似有关。该方法通过对比传统的聚类分割算法和刘华军的改进算法,大大降低了时间复杂度,聚类效果显著。实验证明,该方法收敛性较强,运行时间较短,且具有良好的分割效果。

Abstract: A new image segmentation approach using fuzzy clustering,based on rough set theory,is presented.By extracting encrustation of histogram,and calculating partial fuzzy extent around pixels to update the fuzzy roughness.Using fuzzy roughness and local operator to update the membership function of FCM algorithm.In rough-set theoretic sense,the histogram correlates with the lower approximation and encrustation of histogram correlates with upper approximation.Compared to traditional fuzzy clustering segmentation algorithm and Liu’s approach,not only reduce the time complexity,but also present obviously result of clustering. From the test,the method has stronger convergence,shorter running time,and good segmentation results.

中图分类号: