一种混合搜索优化策略的图像配准方法研究  

Hybrid Search Optimization Strategy of Image Registration Method Research

作　　者：冯雪芳[1] 吴锡生[1] 

机构地区：[1]江南大学物联网工程学院,江苏无锡214122

出　　处：《计算机仿真》2012年第9期274-277,共4页Computer Simulation

基　　金：国家自然科学基金(60973094)

摘　　要：研究图像配准,一般都存在配准精度低,速度慢的不足。为解决上述问题,以归一化互信息作为相似性测度,提出了一种新的混合搜索优化策略:改进的蚁群算法与Powell相结合来优化配准所需的变换参数。利用粒子群算法(PSO)的思想对连续蚁群算法(ACO)的信息素全局更新规则进行改进,并与改进的Powell局部优化算法相结合,得到了亚像素级的配准精度,并且提高了配准效率。实验结果表明,改进算法可保证在全局收敛的基础上,配准精度高,速度较快,具有较好的实用性。Some defects exists in current image registration algorithm, such as low precision and slow speed. In order to improve these problems, we used normalized mutual information as similarity measure, and proposed a new hybrid search optimization strategy： improved ant colony algorithm combined with Powell to optimize the transforma-tion parameters for registration. The algorithm uses the idea of particle swarm optimization algorithm to improve the pheromone updated rules of continuously ant colony algorithm, and combines local optimization algorithm of Powell. The registration precision reaches the sub-pixel level, and it improves the efficiency of registration. Experiments re-sults show that the hybrid algorithm can ensure the global convergence, has a high registration precision and fast reg-istration speed, and has the better application value.

关 键 词：图像配准 归一化互信息 蚁群算法 鲍威尔算法 混合优化算法 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]