多传感器图像自动配准技术是军事领域里多传感器图像融合的必要前提。
Multiple sensor images automated registration is the necessary premise for mutiple sensor image fusion in military field.
在上述改进的角点检测算法基础上，本文提出了结合区域匹配的图像自动配准算法。
Based on the improved corner detection algorithm, an image automatic registration method combined corner detection and area-based matching was developed.
提出了一种基于空间关系一致性的图像自动配准方法，处理具有全局仿射变换的图像配准问题。
An automatic image registration method based on spatial relation consistency is proposed to deal with the registration of images with affine geometric distortion.
为了实现多模态图像间的快速自动配准，本文提出了基于角点检测结合区域匹配的图像自动配准算法。
In order to realize fast automatic registration among multimodal images, an image registration method using both corners and area-based matching is presented in thesis.
基于人工通过地物结构推理匹配关系进行配准的想法，提出了一种基于结构的SAR图像自动配准算法。
Based on the idea that human observers could greatly simplify the matching problem at the level of object structure, a structure-driven SAR image automatic registration algorithm was proposed.
针对基于图像特征点的配准方法中对应特征对难以准确提取的问题，提出一种基于兴趣点匹配的图像自动拼接方法。
Since the corresponding pair of feature points was difficult to be extracted in feature points registration methods, an image mosaic method based on interest point matching was presented.
提出用图像配准方法对发生旋转和平移的两幅图像进行自动配准，该方法已用于射线图像配准，并取得了满意的效果。
An automatic registration method for matching the images translated and rotated has been put forward and applied to radiographic image registration with satisfactory results.
文章实现了一种基于相位一致特征的多光谱图像亚像元波段配准精度自动评价方法。
A high precision method based on the phase congruency features was presented in this paper for automated evaluating sub-pixel band-to-band registration accuracy of satellite multispectral imagery.
将所有点对坐标值代入刚体变换线性方程组，用最小二乘法求出从图像空间到手术空间的刚体变换矩阵，最终实现医学图像标志点的自动识别和配准。
Substituting coordinates of all pairs of points into rigid transform equations, one could use least squares to get the rigid transform matrix from image space to surgical space.
实验表明：基于小波变换的模板相关匹配方案实现了同类传感器遥感图像的自动配准，配准速度快且精度高。
The result shows:the template correlation based on wavelet transformation can realize the automatic registration of the same kind sensing image, with fast speed and high precision.
基于互信息的图像配准方法具有自动化程度高、配准精度高等优点，已被广泛应用于医学图像的配准。
Image registration based on mutual information is of high automatization and high accuracy in registration. Hence, it has been widely exploited in medical image registration.
目前图像配准技术可分为手工配准和自动配准。
Currently image registration technique can be divided into the handicraft technique and automatic technique.
遥感图像的自动配准技术是目前图像配准研究的重点。
With the study of image registration recently, automatic registration of remote sensing image is becoming important.
基于互信息的图像配准方法具有自动化程度高、配准精度高等优点，近年来在医学图像配准中得到广泛应用。
Mutual information-based image registration has been widely exploited due to its high-level automation and accuracy, especially in medical image registration.
针对图像处理领域中遥感图像的配准问题，提出一种基于图像局部特征的快速、自动配准方法。
The fast auto registration of remote sensing image is a very important problem. In this paper, local feature of image is utilized to realize the fast auto registration of remote sensing image.
基于互信息的配准方法，包括互信息和归一化互信息方法，是目前医学图像配准中无创、自动且精度很高的一种方法，已经被广泛应用。
Image registration methods based on mutual information, including mutual information and normalized mutual information, have been accepted as the most accurate and efficient methods.
印章自动鉴定属于图像模式识别领域，其主要分为印文分割、印文配准、特征提取及特征识别几个步骤。
Automatic seal identification belongs to pattern recognition domain and includes seal segmentation, seal registration, feature extraction and feature identification these steps.
提出了一种全自动、多模态的信息融合解决方案用于配准视频图像和磁跟踪数据。
The paper reports a fully-automated, multiple-modality sensor data registration scheme between video and magnetic tracker data.
本文提出的算法适应性较强，在重复性纹理、旋转角度比较大等较难自动匹配场合下仍可以准确实现图像配准。
In this paper, the algorithm adapted, in the repetitive texture, such as relatively large rotation more difficult to automatically match occasions can still achieve an accurate image registration.
本文提出的算法适应性较强，在重复性纹理、旋转角度比较大等较难自动匹配场合下仍可以准确实现图像配准。
In this paper, the algorithm adapted, in the repetitive texture, such as relatively large rotation more difficult to automatically match occasions can still achieve an accurate image registration.
应用推荐