基于HD距离与混合优化算法的图像配准  

An Image Registration Approach Using Improved Hausdorff Distance Combined with the Multipled Optimization algorithm

作　　者：林莹[1] 王娜[1] 张静[1] 于战科[1] 

机构地区：[1]解放军理工大学理学院,南京211101

出　　处：《微计算机信息》2011年第1期142-144,共3页Control & Automation

摘　　要：提出一种基于改进型Hausdorff距离与粒子群优化(PSO)算法相结合的图像配准方法。首先运用Harris角点检测算子进行特征点提取,利用一种改进型Hausdorff距离作为配准的相似性测度,然后用PSO算法和Powell方法相结合的混合优化算法求解空间变换参数,仿真结果表明此算法准确有效,并能够减少计算量。A novel method combined the improved Hausdorff distance（HD） with Particle swarm optimization（PSO） was provided.Firstly,the method apply Harris corner detector to realize extracted feature points;Then the improved Hausdorff distance is regarded as the registration principle;finally,the translation parameters are calculated by using PSO algorithm combined with Powell ＇s method.Simulation results show that the algorithm is effective and accuracy;and it could reduce the amount of computation largely.

关 键 词：图像配准 HAUSDORFF距离 粒子群算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]