基于NSCT变换的红外与可见光图像融合方法  

Infrared and visible image fusion method based on developed NSCT transform

作　　者：陈天华[1] 林雨辰 

机构地区：[1]北京工商大学计算机与信息工程学院,北京100048

出　　处：《北京交通大学学报》2013年第6期18-21,共4页JOURNAL OF BEIJING JIAOTONG UNIVERSITY

基　　金：北京市教委科技创新平台资助项目(201151);北京市教委科技发展计划项目资助(KM201210011003)

摘　　要：针对小波变换不能很好地表达图像边缘信息,NSCT变换对图像细节信息表达缺失的问题,本文提出了一种改进的基于NSCT变换的图像融合方法.首先将经过预处理和配准后的红外图像和可见光图像进行NSCT变换,得到各个源图像的低频和高频系数,然后对分解后的低频系数采用小波变换的融合规则进行融合处理,高频系数则采用基于特征的区域能量的融合规则进行融合处理,最后对融合后的系数进行NSCT反变换得到融合图像.仿真实验表明,采用改进的NSCT融合方法对红外与可见光图像的融合有良好的效果,图像更清晰,信息更全面.According to the image edge information unclearly expressed with wavelet transform and the missing of image detail information expression with NSCT transform, this paper presents an improved image fusion method based on NSCT transform. Firstly, we make NSCT transform for the infrared and visible image after preprocessing and registration, so we get the different frequency NSCT coeffi- cients of source images, then we separately do image fusion for different frequency domain after de- composition according to the rule that is the low frequency NSCT coefficients using wavelet transform and the high frequency NSCT coefficient selecting regional large. Meanwhile, we compare it with oth- er fusion algorithms. The simulation experiment results show that using this method has a good effect on the infrared and visible image fusion which is more clearly and completely.

关 键 词：图像融合 NSCT变换 红外图像与可见光图像 仿真实验 

分 类 号：TN911.73[电子电信—通信与信息系统]