配准测度的鲁棒性是图像配准过程中经常要考虑的问题之一。
The robustness of registration measures is one of the most frequently considered problems in image registration process.
结果表明：这几种配准测度和重叠面积的线性相关关系特别显著。
The results indicate that the linear correlativity between these registration measures and overlay area is very prominent.
提出了一种新的基于区域互信息和局部频率信息结合的双向图像配准测度。
In this paper, a new bilateral registration measurement based on regional information and local frequency information is presented.
特征空间、几何变换、相似性测度以及优化算法是设计医学图象配准方法时要考虑的四个主要因素。
Many investigator explore in the domain. Medical images registration methods have four main factors: features space, geometry transformation, similarity, and optimizing algorithm.
方法在极端的刚体配准条件下，检验出互相关系数，互信息和相关比相似性测度为适合的相似性测度。
Method Under extreme rigid registration condition, correlation coefficient, mutual information and correlation ratio similarity measures were tested as most suitable similarity measures.
提出一种利用局部互相关系数作为相似性测度的灰度一致性配准算法。
The consistency registration algorithm, which used local cross correlation coefficient as the similarity metric, was proposed.
传统的图像配准的相似性测度函数对噪声过于敏感，且需要先验知识约束。
Traditional resemblance measurement function is application-restricted since it is too sensitive to noise and is subject to prior knowledge.
实验表明，在多数情况下，互信息的配准精度是这三种相似性测度中最高的。
The results of experiments show that these similarity measure methods have different effect and performance in the different application circumstances, but the mutual information is more precise.
在基于体素灰度的医学图像配准领域，本文采用了全新的相关比相似性测度作为配准的测度准则。
A new correlation ratio similarity measure in voxel intensity based medical image registration field was adopted.
在基于体素灰度的医学图像配准领域，本文采用了全新的相关比相似性测度作为配准的测度准则。
A new correlation ratio similarity measure in voxel intensity based medical image registration field was adopted.
应用推荐