Computer Engineering and Applications ›› 2009, Vol. 45 ›› Issue (22): 172-174.DOI: 10.3778/j.issn.1002-8331.2009.22.056

• 图形、图像、模式识别 • Previous Articles     Next Articles

Multi-image registration based on entropy of normalized mutual information vector

WANG Guang-tai1,HU Shun-bo1,LIU Chang-chun2,SHAO Peng3,YANG Ji-hong4   

  1. 1.Department of Physics,Linyi Normal University,Linyi,Shandong 276005,China
    2.School of Control Science and Engineering,Shandong University,Jinan 250061,China
    3.Department of Radiology & Diagnostic Imaging,University of Alberta,Edmonton T6G2E1,Canada
    4.School of Computer,Liaocheng University,Liaocheng,Shandong 252059,China
  • Received:2008-06-03 Revised:2008-07-28 Online:2009-08-01 Published:2009-08-01
  • Contact: WANG Guang-tai

基于归一化互信息向量熵的多幅图像配准方法

王广泰1,胡顺波1,刘常春2,邵 鹏3,杨吉宏4   

  1. 1.临沂师范学院 物理系,山东 临沂 276005
    2.山东大学 控制科学与工程学院,济南 250061
    3.阿尔伯塔大学 放射与诊断影像学系,爱德芒顿市 T6G2E1
    4.聊城大学 计算机学院,山东 聊城 252059
  • 通讯作者: 王广泰

Abstract: A novel method for multi-image registration is proposed,which is called the entropy of normalized mutual information vector.This method first calculates joint probability distribution of any two images,and then calculates the normalized mutual information according to it.All the normalized mutual information of two images forms a vector,the normalized mutual information vector.At last the entropy of that vector is calculated.The maximal entropy corresponds to the optimal registration solution.The function curves,computing time and registration accuracy are studied by applying the new method and other three methods to rigid registration of brain images.The obtained results show that the proposed method can improve registration accuracy and decrease registration time.

Key words: medical image registration, normalized mutual information vector, joint probability distribution, entropy

摘要: 提出了一种新的多幅图像配准方法,归一化互信息向量熵方法。这种方法先计算任意两幅图像间的联合概率分布,然后根据联合概率分布计算它们间的归一化互信息,把所有两幅图像组合得到的归一化互信息组成一个向量,最后计算该归一化互信息向量的熵。最大熵对应最佳配准位置。通过对人体脑部图像的刚体配准实验,从函数曲线、计算时间和配准精度方面,对新方法和其它三种方法进行了分析和比较。实验结果表明,新提出的方法可以提高配准精度、减少配准时间。

关键词: 医学图像配准, 归一化互信息向量, 联合概率分布,