计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (34): 225-226.DOI: 10.3778/j.issn.1002-8331.2009.34.070

• 工程与应用 • 上一篇    下一篇

融入空间信息的医学图像优质分割

辛学刚,卢振泰,陈武凡   

  1. 南方医科大学 生物医学工程学院,广州 510515
  • 收稿日期:2008-07-07 修回日期:2008-12-10 出版日期:2009-12-01 发布日期:2009-12-01
  • 通讯作者: 辛学刚

Medical image segmentation incorporate with spatial information

XIN Xue-gang,LU Zhen-tai,CHEN Wu-fan   

  1. School of Biomedical Engineering,Southern Medical University,Guangzhou 510515,China
  • Received:2008-07-07 Revised:2008-12-10 Online:2009-12-01 Published:2009-12-01
  • Contact: XIN Xue-gang

摘要: 传统的FCM分割算法只考虑到图像的灰度信息,而忽略了灰度的空间信息,对于迭加了噪声的图像,难以得到准确的结果。从马尔可夫随机场(MRF)中得到启示,考虑到图像灰度信息及其空间分布出发,提出了一种新的基于邻域(Neighbor)信息FCM分割算法,即NFCM算法。实验结果表明该算法所得到的目标图像的边界特征保持完好,图像边界细腻、连续且定位性能好。

Abstract: The conventional FCM don’t take into account the spatial information of image and can get the unexpected results of segmentation when dealing with some image contaminated by noise.Inspired by the MRF model,considering the pixel and its neighbor,an improved model is presented to fuzzy C-means algorithm using neighborhood information.The proposed algorithm can reasonably use the spatial information of image and improve the accuracy of segmentation.The results of experiments show that the proposed algorithm can provide powerful image segmentation than many segmentation algorithms.

中图分类号: