基于有限脊波变换的图像融合方法  

Novel algorithm of multi-sensor image fusion using FRIT

作　　者：苗启广[1] 王宝树[1] 

机构地区：[1]西安电子科技大学计算机学院,陕西西安710071

出　　处：《系统工程与电子技术》2008年第7期1347-1350,共4页Systems Engineering and Electronics

基　　金：国家自然科学基金(60702063);广西壮族自治区青年科学基金(桂科青0640067)资助课题

摘　　要：针对小波变换在进行图像处理时不能有效表示直线/曲线的奇异性问题,研究了能够很好表示二维或更高维奇异性的有限脊波变换的基本原理,讨论了将有限脊波变换应用于图像融合的可行性,提出了基于有限脊波变换方法进行图像融合的基本架构,并对变换系数的设置与融合过程的处理进行了详细说明。仿真实验的主客观性能比较表明,基于有限脊波变换的图像融合方法比基于金字塔变换和基于小波变换方法的融合效果要好得多。The problem that the contour segment of 2-dimensional image could not be gotten perfectly with wavelet transform in image processing is analyzed. The linear and curve singularity could not be expressed by wavelet transform. Then, the principal of finite ridgelet transform and its good performance in expressing the singularity of 2-dimensional or high dimensional are studied. The feasibility of image fusion using finite ridgelet transform is discussed in detail. A new fusion method based on finite ridgelet transform and its fusion frame- work are proposed. The coefficients structure and the fusion procedure are given in detail. Experiments show that the proposed algorithm works better in preserving the edge and texture information than other methods do in image fusion.

关 键 词：图像融合 有限脊波变换 有限RADON变换 奇异性 

分 类 号：TN911.73[电子电信—通信与信息系统] TP183[电子电信—信息与通信工程]