Computer Engineering and Applications ›› 2009, Vol. 45 ›› Issue (14): 204-206.DOI: 10.3778/j.issn.1002-8331.2009.14.063

• 工程与应用 • Previous Articles     Next Articles

Application of M-estimation in medical images registration

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

  1. School of Biomedical Engineering,Southern Medical University,Guangzhou 510515,China
  • Received:2008-03-17 Revised:2008-05-19 Online:2009-05-11 Published:2009-05-11
  • Contact: XIN Xue-gang

M估计在医学图像配准中的应用

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
  • 通讯作者: 辛学刚

Abstract: Rigid image registration or matching is a difficult problem in image processing filed.Noise and outlines can play havoc with conventional least-squares estimation,this paper presents a new alignment algorithm relies on M-estimation,which automatically ignores pixel where the intensities are sufficiently different in the two images.A multi-resolution pyramid implementation enables the algorithm to estimate large displacements.Experimental results show robustness and effectiveness of this method.

Key words: M-estimation, image registration, least squares, multi-resolution

摘要: 图像的刚性配准或者匹配是图像处理中的热点和难点问题。由于图像的不连续性和成像设置中噪声的影响,传统的最小二乘方法(Least Squares Method)不能很好地解决这一难题。采用M估计算子(M-estimation operator)代替最小二乘算子,并结合由粗到精的多分辨率策略,提出了一种新的基于M估计的医学图像多分辨率配准算法,实验结果表明该方法对配准的速度、精度及鲁棒性都有很大的提高。

关键词: M估计, 图像配准, 最小二乘, 多分辨率