方法采用最大互信息法对6例患者PET和MRI三维脑图像进行刚体配准。
Methods Maximization of mutual information method was used in the rigid registration for PET and MRI images of 6 patients.
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.
为满足航空发动机精铸涡轮叶片壁厚偏差分析需要，提出了一种基于变形函数的精铸涡轮叶片检测模型非刚体配准算法。
To satisfy the need of blade geometry inspection and deviation analysis of aero-engine, a non-rigid registration algorithm based on deformation function is proposed.
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.
最后对待配准图像进行刚体变换及双线性插值，从而实现图像配准。
Finally, the rigid transformation and bilinear interpolation in the image prepared for registration is carried out to realize image registration.
最后对待配准图像进行刚体变换及双线性插值，从而实现图像配准。
Finally, the rigid transformation and bilinear interpolation in the image prepared for registration is carried out to realize image registration.
应用推荐