摘要
提出一种新的基于互信息和小波分析的混合优化配准算法,在最低分辨率下用模拟退火算法进行全局优化,在高分辨率下采用Powell算法进行优化.结果显示:该方法用于医学图像配准,并与已有的传统方法进行分析比较,具有良好的全局优化性能和时间性能.
In this paper, a new method based on mutual information, wavelet decomposition, and hybrid optimization is proposed for medical image registration. Two kinds of optimization were performed. One is global optimization using simulate anneal algorithm under the lower resolution rate and the other is to employ the Poweli algorithm under higher resolution rate. Results show that a new method is suitable to medical image registration and has a good global optimization and runtime performance.
出处
《海南大学学报(自然科学版)》
CAS
2006年第4期406-411,共6页
Natural Science Journal of Hainan University
基金
国家自然科学基金(60573019)
广东省自然科学基金(05103541
31340)
关键词
互信息
小波分解
混合优化
医学图像配准
mutual information
wavelet decomposition
hybrid optimization
medical image registration