基于混合优化算法的医学图像配准方法

A medical image registration algorithm based on hybrid optimization algorithm

基于互信息的图像配准算法计算复杂度高,配准速度慢。针对这一问题,本文提出一种基于改进遗传算法和Powell算法相结合的医学图像配准方法。首先针对传统遗传算法收敛速度慢、易早熟的缺陷,本文对遗传操作中的交叉运算过程提出了改进策略,并将改进的遗传算法与Powell算法相结合,充分利用遗传算法的全局搜索能力与Powell算法的局部搜索能力。与Powell算法和未改进的遗传算法相比,本文提出的算法极大地缩短了图像配准所用的时间,同时提高了算法的抗噪性。

Image registration algorithm based on mutual information has high complexity and low speed.To solve the problem , a new image registration method based on improved genetic algorithm and Powell algorithm is proposed in this paper .Considering the shortages of the standard genetic algorithm , such as prematurity and slow convergence that may result in mismatching , in this paper , we improve the crossover operation of the genetic operations .At the same time , we combine the improved genetic algorithm and Powell algorithm.The method makes full use of the global search capability of genetic algorithm and the local search capability of Powell algorithm.Compared with Powell algorithm and the traditional genetic algorithm , this algorithm we proposed can effectively improve the image registration velocity and noise immunity .