摘要
提出了改进图像配准的基于互信息的算法,首先将参考图像和待配准图像分解到小波域并二值化,以归一化互信息作为相似性测度进行配准。配准参数搜索作用SPSA算法和鲍威尔算法相结合的优化策略。实验证明本算法可以快速、精确且不需要人工干预地实现两幅图像的配准。
An improved algorithm of image registration based on mutual information was proposed, the reference image and registered image were decomposed into wavelet field and binaried. The normalized mutual information was used to be a scale of similarity to two registered images. SPSA algorithm and Powell algorithm were combined to optimize the parameter searching process. Experiments show that this algorithm can register two images rapidly, accurately and automatically.
出处
《激光与红外》
CAS
CSCD
北大核心
2007年第5期470-473,共4页
Laser & Infrared
基金
国防基础科研项目基金(K1305060614)
关键词
图像配准
互信息
小波分解
SPSA算法
鲍威尔法
image registration
mutual information
wavelet decomposition
SPSA algorithm
Powell algorithm
