摘要
针对互信息配准方法中目标函数因存在多极值而容易陷入局部最优的问题,提出了一种基于萤火虫算法改进优化策略的互信息医学图像配准算法。该算法使用归一化互信息作为相似性测度,用萤火虫所处位置来表示配准参数,根据每个萤火虫的位置计算互信息函数值并将其作为当前萤火虫的亮度,通过亮度和吸引度的迭代更新来寻找互信息函数取最优解时的最佳配准参数。实验结果表明,该方法克服了互信息函数容易陷入局部最优的问题,有效地提高了配准精度。
To solve the problem that the object function is easy to get into local optimalization because of much local ex- tremes in the mutual information registration method, a mutual information medical image registration algorithm based on firefly algorithm was put forward. The normalized mutual information is used as the similarity measure and registra- tion parameters are expressed by the locations of fireflies in the algorithm, and mutual information function values are calculated according to the locations of fireflies and are set as brightness values of fireflies, and the best registration pa- rameters are retrieved by updating the brightness and attractiveness iteratively while the mutual information function reaches the maximum value. The experimental results indicate that this algorithm can effectively overcome the problem that the mutual information function is easy to fall into local optimalization, and the precision of registration result is im- proved obviously.
出处
《计算机科学》
CSCD
北大核心
2013年第7期273-276,共4页
Computer Science
基金
国家自然科学基金项目(60962004
61162016)
甘肃省科技支撑计划项目(1104FKCA102)资助
关键词
图像配准
互信息
萤火虫算法
Image registration, Mutual information, Firefly algorithm
