On the one hand we analyze the problems when classic feature extraction methods used on sar image ; on the other hand , we design experiments to choose for a proper similarity criterion for sar image , and use this criterion in the following sar image registration method 一方面分析了传统特征提取方法应用于sar图像时面临的问题，另一方面通过实验选取适合于sar图像的局部区域相似性度量准则，为下一步新图像配准方法的设计提供依据。
For elastic reigistration of non - rig id body , after the thin - plate splines for image registration is analysed , the local elastic registration is presented , which usilizes a positive definite function with compact support as the radial basis function of interpolation 对于非刚性物体图像的弹性配准，本文先分析了基于薄板样条弹性配准方法，总结了其不足之处，通过采用一种紧支正定函数作为插值方法中的径向基函数，实现了图像的局部弹性配准。
The primary content andcontributions of this paper are as follows : first , it delves into the key technique of electronic image stabilizing algorithm ? ? imageregistration , and brings forward a feature based registration method which is from coarse toprecise , and form local matching to global registration 论文的主要研究内容包括以下三个方面:首先,对电子稳像算法中的关键技术? ?图像配准进行了深入研究,提出一种基于特征的由粗到精、由局部到全局的配准方法。
This paper presents monomodality registration of rigid body , elastic rigistration of non - rigid body and interpolation used in image registration . by comparison of several interpolations , because of the best tradeoff between accuracy and the computational cost , cubic spline interpolation is selected as interpolation of this paper ' s registration 首先通过对配准中所采用的几种插值算法进行了比较，选出了有较高插值质量和有较高计算效率的三次样条插值算法作为本文中配准方法所采用的插值。
For global registration of rigid body , based on analysis of the principal axes method , by making use of automatic and very fast nature , and easy implementation of the method , a registration method of principal axes - information is presented to remedy drawback of coarse result 针对单模刚体全局配准，先分析了基于主轴配准法的配准原理，再在此基础上，利用其计算速度快、全自动化以及容易实现的优点，并针对其配准精度不高的不足，提出了一种基于主轴信息的配准方法。
The outline of our research is to put forward a solution of medical image fusion that is based on analyzing current data of medical images and an induction of the methods of image fusion . first , we extract the organic contour of the medical images . then do image registration based on organic contour extraction 我们的基本研究思路是：在进行广泛的资料收集，对现有的医学图像资料数据和图像配准方法进行分析、归纳的基础上，提出一套医学图像信息融合的解决方案? ?首先提取医学图像中人体器官的轮廓，再在器官轮廓的基础上进行图像配准，最后利用小波变换实现医学图像信息融合。
Second , more feature points are extracted for advanced registration based on projective transformation . compared with the ordinary method , our method has a better robust feature with higher accuracy , it also has a fully automatic feature so it need little human intervention in the whole process . the image segmentation , feature extraction , feature correspondency , and transformation model of multi - modality medical image registration are also studied in this paper 本研究的创新之处:针对rf和fa视网膜图像的特点，提出了新的血管细化的新方案;在特征点提取方面，提出了“三轮定心”这种新的特征点提取方法;提出了由“粗配”到“细配”的混合配准方法;力矩主轴法用于图像配准参数的估计及对应性尺度参数范围的定值。
On the base of introducing basic theories about image fusion , the article narrates the methods and technical development of image fusion . in allusion to pixel - level fusion , the algorithm of image registration is studied and the method of image characteristic registration based on sobel quick edge - detection is presented 本文在介绍图像融合基本理论的基础上，简述了图像融合的方法及技术发展，针对像素级的图像融合研究了图像配准的方法，提出了基于sobel快速边缘检测的特征配准方法。
2 . the conception of the platform alignment and system alignment is presented for multi - platform multi - sensor and multi - source information fusion with systematic temporal and spatial alignment based on the different spatial distributions between single - platform and multi - platforms . to do as this , we can deal with different problem with different alignment approaches , and it is propitious to solve the problem 针对单平台和多平台传感器空间布局的不同特点，提出了多平台多传感器信息融合系统传感器时空配准的平台级配准和系统级配准概念，使得我们在处理不同问题时采用不同的配准方法，更有利于问题的解决。
Then the major registration algorithms and categories are described . the knowledge about mi and the affection of interpolation , outlier strategy and grey levels was discussed in detail . unfortunately , the mi based registration has lots of disadvantages : mi is computing expansive , the registration process is slow , and the mutual information function is generally not a smooth function but one containing many local maxima , which has a large influence on optimization 本文对多模医学图像配准进行了研究,所做的主要工作有:首先介绍了多模医学图像配准的概念和配准过程,对目前主要的配准方法及其分类进行了归纳,详细讨论了互信息的相关知识以及插值方法、出界点处理和灰度级数目对互信息配准的影响。
