作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2012, Vol. 38 ›› Issue (14): 193-195. doi: 10.3969/j.issn.1000-3428.2012.14.058

• 图形图像处理 • 上一篇    下一篇

改进FCM在医学图像分割中的应用

张保威,钱慎一,宋宝卫   

  1. (郑州轻工业学院计算机与通信工程学院,郑州 450002)
  • 收稿日期:2011-11-14 出版日期:2012-07-20 发布日期:2012-07-20
  • 作者简介:张保威(1980-),男,讲师、硕士,主研方向:智能信息处理,模式识别;钱慎一,副教授、硕士;宋宝卫,讲师、硕士
  • 基金资助:
    河南省教育厅自然科学研究计划基金资助项目(2011A5 20047);河南省教育厅科学技术研究基金资助重点项目(12B520070)

Application of Improved FCM in Medical Image Segmentation

ZHANG Bao-wei, QIAN Shen-yi, SONG Bao-wei   

  1. (School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China)
  • Received:2011-11-14 Online:2012-07-20 Published:2012-07-20

摘要: 针对传统模糊C均值(FCM)未考虑邻域信息引起的局部收敛性差、效率低等问题,提出一种基于粗糙度的改进FCM算法。利用包含空间信息和灰度信息的窗口构造直方图上近似,并进一步获取图像粗糙度,从而确定初始聚类中心,实现医学图像的分割。实验结果表明,与传统FCM算法相比,改进算法不仅能分割出图像中的全局成分,而且具有较高的运行效率。

关键词: 模糊C均值, 粗糙度, 医学图像分割, 离散化, 聚类

Abstract: The traditional Fuzzy C-Means(FCM) ignores considering the neighborhood information, so it has low efficiency and poor global convergence. In order to solve these problems, this paper uses the window including space and gray information and by improving Histion and constructing roughness, roughness-based FCM for medical image segmentation is proposed in this paper. Experimental results verify the corresponding advantages of the proposed algorithm. Compared with traditional FCM, the proposed method can retrieve global difference in the image, together with high efficiency.

Key words: Fuzzy C-Means(FCM), roughness, medical image segmentation, discretization, clustering

中图分类号: