北京生物医学工程
北京生物醫學工程
북경생물의학공정
BEIJING BIOMEDICAL ENGINEERING
2015年
3期
234-238
,共5页
别术林%刘杰%唐子淑%邱禧荷
彆術林%劉傑%唐子淑%邱禧荷
별술림%류걸%당자숙%구희하
互信息%Powell算法%遗传算法
互信息%Powell算法%遺傳算法
호신식%Powell산법%유전산법
mutual information%Powell algorithm%genetic 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。
基于互信息的圖像配準算法計算複雜度高，配準速度慢。針對這一問題，本文提齣一種基于改進遺傳算法和Powell算法相結閤的醫學圖像配準方法。首先針對傳統遺傳算法收斂速度慢、易早熟的缺陷，本文對遺傳操作中的交扠運算過程提齣瞭改進策略，併將改進的遺傳算法與Powell 算法相結閤，充分利用遺傳算法的全跼搜索能力與Powell算法的跼部搜索能力。與Powell算法和未改進的遺傳算法相比，本文提齣的算法極大地縮短瞭圖像配準所用的時間，同時提高瞭算法的抗譟性。
기우호신식적도상배준산법계산복잡도고，배준속도만。침대저일문제，본문제출일충기우개진유전산법화Powell산법상결합적의학도상배준방법。수선침대전통유전산법수렴속도만、역조숙적결함，본문대유전조작중적교차운산과정제출료개진책략，병장개진적유전산법여Powell 산법상결합，충분이용유전산법적전국수색능력여Powell산법적국부수색능력。여Powell산법화미개진적유전산법상비，본문제출적산법겁대지축단료도상배준소용적시간，동시제고료산법적항조성。
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 .
