一种基于互信息和小波分解的图像配准算法  

A Novel Image Registration Method Based on Wavelet Decomposition and Mutual Information

作　　者：李卫华[1] 周军[1] 周连文[1] 程英蕾[2] 

机构地区：[1]西北工业大学航天学院,西安710072 [2]空军工程大学电讯工程学院,西安710077

出　　处：《计算机工程与应用》2005年第33期31-33,47,共4页Computer Engineering and Applications

摘　　要：为了寻找快速、精确、鲁棒性强的自动配准算法,论文提出了基于互信息和小波分解图像配准方法。假设实时图像和模板图像之间的变换为仿射变换,采用金字塔小波分解和边缘特征提取获得特征点,利用分层特征点方法进行配准,以互信息最大作为度量准则,在每层上利用互信息的最大值来获取变换参数,然后得到全局变换参数。仿真结果表明此方法具有很好的抗干扰性、鲁棒性和精确性。The Image registration is one of the most key techniques in image analysis and image understanding.h has been widely used in many areas,such as,change detection in remote sensing,medical treatment,target recognition,image fusion,navigation and location,image movement analysis and machine vision.In order to develop a quick,accurate and anti-noises automated image registration algorithm,this paper presents a novel feature-matching algorithm is adopted.And the transform parameters are gotten by the maximum mutual information as a metric.The parameters include translation, rotation and scale change.The simulation results for remote images show that the method can effectively and accurately work.

关 键 词：互信息 小波分解 图像配准 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]