基于相似度比较的图像灰度匹配算法研究  

Study on the image grayscale matching algorithm based on similarity measures

作　　者：杨小冈[1] 曹菲[1] 缪栋[1] 张云鹏[1] 

机构地区：[1]第二炮兵工程学院303教研室,陕西西安710025

出　　处：《系统工程与电子技术》2005年第5期918-921,共4页Systems Engineering and Electronics

基　　金："十五"国防重点科研项目基金资助课题(413220209)

摘　　要：为提高图像灰度匹配算法的匹配性能,分析了常用的图像相似度比较方法,从实际应用出发,提出了一种简化的归一化积相关度量方法。针对景像匹配末制导,设计了先粗后精的匹配控制策略,实现了归一化积相关图像匹配算法的有效加速,并给出了简化的快速算法的基本设计思想。通过大量的匹配仿真实验,系统分析了算法对灰度畸变、噪声干扰、几何旋转畸变以及制导图大小的适应性。仿真实验结果验证了所给匹配控制策略的有效性、实用性以及算法的优越性。To improve the performance of image grayscale matching algorithm, a novel image similarity measure and image matching algorithm is studied. Firstly, the conventional image similarity measures are analyzed and a simplified normalized product correlation similarity measure is proposed for practical application. Then, an approach which can accelerate the normalized product correlation matching algorithm is designed and implemented by adopting 'from coarse to precise' control strategy, and the basic design idea of the simplified fast algorithm is given. Finally, adaptability of the algorithm to grayscale distortion, noise disturbance, geometric rotation and size of image for guidance is systematically studied. The simulation experimental results demonstrate the efficiency and practicability of the matching control strategy and the advantage of the proposed algorithm.

关 键 词：图像匹配 相似度比较 归一化积相关 控制策略 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]