计算机工程与应用 ›› 2007, Vol. 43 ›› Issue (26): 203-205.

• 工程与应用 • 上一篇    下一篇

一种结合空间信息的FCM算法对脑MR图像的分割

张 兰,王 珂,杨文宏   

  1. 吉林大学 通信工程学院,长春 130025
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-09-11 发布日期:2007-09-11
  • 通讯作者: 张 兰

FCM algorithm with spatial information for segmentation of brain MRI

ZHANG Lan,WANG Ke,YANG Wen-hong   

  1. College of Communication Engineering,Jilin University,Changchun 130025,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-09-11 Published:2007-09-11
  • Contact: ZHANG Lan

摘要: 根据局部统计信息引入一个控制参数用于区分某个空间邻域中的噪声点、边缘点和区域内部的点,提出一种合理利用空间信息对隶属度更新的FCM算法。仿真结果表明,使用该算法对附加有偏差场和噪声的脑MR图像进行分割,所得的结果相对于FCM算法和一些改进的算法具有更好的紧致性和分离性。

关键词: 模糊C均值聚类, 图像分割, MR图像, 偏差场, 空间信息

Abstract: Uses a statistical method to introduce a control parameter that can distinguish the pixel of a spatial neighborhood whether it is a noise,an edge or inside an area.So presents a proposed Fuzzy C-Mean(FCM) algorithm that uses the spatial information to update the membership.The simulation results show that the proposed algorithm can provide a more powerful result than FCM algorithm and others.

Key words: Fuzzy C-Mean(FCM) clustering, image segmentation, brain magnetic resonance image, bias field, spatial information