邻域灰度与空间特征相结合的互信息配准方法研究

中国机械工程 ›› 2011, Vol. 22 ›› Issue (4): 439-443.

邻域灰度与空间特征相结合的互信息配准方法研究

魏玉兰;颜云辉;李兵;张尧;李骏

东北大学,沈阳,110004

出版日期:2011-02-25 发布日期:2011-03-15
基金资助:
国家自然科学基金资助项目(50574019)；国家高技术研究发展计划(863计划)资助项目(2008AA04Z135)；中央高校基本科研业务费专项资金资助项目(90603004)
National Natural Science Foundation of China（No. 50574019）;

National High-tech R&D Program of China (863 Program) （No. 2008AA04Z135）;
Fundamental Research Funds for the Central Universities( No. 90603004 )

Research on Mutual Information Registration Combined Neighborhood Intensity with Spatial Signature

Wei Yulan;Yan Yunhui;Li Bing;Zhang Yao;Li Jun 

Northeastern University,Shenyang,110004

Online:2011-02-25 Published:2011-03-15
Supported by:

National Natural Science Foundation of China（No. 50574019）;

National High-tech R&D Program of China (863 Program) （No. 2008AA04Z135）;
Fundamental Research Funds for the Central Universities( No. 90603004 )

摘要/Abstract

摘要：

针对互信息配准方法存在受噪声影响大、忽略空间信息会引起配准误差的问题,提出一种结合邻域灰度及空间几何特征的互信息相似性测度计算方法。该测度计算方法利用了待配准图像间的灰度互信息,同时又充分结合了邻域内像素间的几何距离及灰度变化关系。在互信息计算时,图像中每个像素的灰度值由其邻域内像素的灰度值按照距离及灰度变化关系分配不同的权值共同得到。实验结果表明,与归一化互信息和梯度互信息法配准结果相比,该方法得到的配准精度更高,抗高斯噪声干扰性能更好。

关键词:

图像配准, 互信息, 邻域信息, 灰度变化相似度, 空间位置相似度

Abstract:

In order to overcome the shortcomings of mutual information

registration,such as susceptible to noise and registration errors caused by ignore the spatial signature, a new similarity measure of mutual information method was proposed,

which combined intensity with geometric characteristics of the neighborhood . The method took advantage of the intensity mutual information, while fully integrating the neighborhood of

the geometric distance between pixels and the relation between intensity. In the calculation of mutual information, every pixel was determined by neighborhood pixel according to weight value by distance and intensity changing relationship.Experimental results show that compared with traditional mutual information and gradient mutual information,the new registration method is more accurate, and anti-Gaussian-noise performance is better.

Key words:

image registration, mutual information, neighborhood information, similarity of intensity change, spatial similarity

中图分类号:

TP391.41

魏玉兰, 颜云辉, 李兵, 张尧, 李骏.

邻域灰度与空间特征相结合的互信息配准方法研究

[J]. 中国机械工程, 2011, 22(4): 439-443.

WEI Yu-Lan, YA Yun-Hui, LI Bing, ZHANG Yao, LI Jun.

Research on Mutual Information Registration Combined Neighborhood Intensity with Spatial Signature

[J]. China Mechanical Engineering, 2011, 22(4): 439-443.

[1]	刘彬1;刘永记1;刘浩然1;李雷2;孙美婷1. 基于贝叶斯改进结构算法的回转窑故障诊断模型研究[J]. 中国机械工程, 2017, 28(18): 2143-2151.
[2]	陈建国;王奉涛;朱泓;张志新;李宏坤;. 改进ICA与HHT在转子故障诊断上的应用[J]. J4, 2009, 20(17): 0-2021.