...归一化互信息,[gap=1226]t features transform, Image registration, Multi-scale Harris corner detection, Normalized mutual information, ...
基于32个网页-相关网页
The metric of the precise registration is combining normalized mutual information and gradient similarity. Powell is used as the optimization to calculate the final parameters.
精配准过程中利用归一化互信息与梯度相似性相结合作为配准的相似性测度,使用Powell优化算法进行搜索,得到最终的配准参数。
参考来源 - 基于Radon变换的多模态医学图像配准·2,447,543篇论文数据，部分数据来源于NoteExpress
Normalized mutual information was adopted as the similarity measure.
使用归一化互信息作为相似性量度。
Image registration methods based on mutual information, including mutual information and normalized mutual information, have been accepted as the most accurate and efficient methods.
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。
This paper aims to research registration of CT and MRI images of caput based on gradient and normalized maximization mutual information method.
本文研究了基于最大互信息和图象梯度组合的人脑CT与MRI多模医学图象配准算法。
应用推荐