高级检索

图像配准中确定性扰动PV插值算法

Deterministic Perturbation PV Interpolation in Image Registration

  • 摘要: 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,图像插值是图像配准过程中一个十分关键的步骤详细分析了各类插值算法的优缺点,提出了一种确定性扰动PV插值算法,在利用PV插值时考虑了随机扰动涉及到扰动点周围9个网格点,并且通过扰动确定化计算PV插值法的权值实验结果表明:该算法能够避免网格点和非网格点上的局部极值,有效地改善了基于互信息的目标函数的性能,使函数更加平滑.

     

    Abstract: During the interpolation process of Partial Volume Distribution, the random perturbation relating to the nine grid points around the perturbing point is taken into account, and the perturbation is evatuated to calculate the weights in PV interpolation. Experimental results indicate this algorithm can avoid the local extremum on grid points and non-grid points, and effectively smooth the object function through mutual information.

     

/

返回文章
返回