基于Directionlets和PCA的多光谱与全色图像融合  

Multispectral and Panchromatic Images Fusion Based on Directionlets

作　　者：张健[1] 陈孝威[1] 

机构地区：[1]贵州大学计算机科学与信息学院,贵阳550025

出　　处：《计算机科学》2012年第3期249-250,264,共3页Computer Science

基　　金：贵州省优秀教育科技人才省长专项资金项目(200714)资助

摘　　要：基于数字化线段理论和整数栅格理论的Directionlets不仅继承了小波变换维数可分性的特点,而且通过选择变换方向和队列方向来获得灵活的多方向性,从而得到能够更好地捕获图像方向信息的方向各向异性的基函数。首先基于Directionlets和PCA的全色和多光谱图像融合方法,对多光谱图像进行线性PCA变换,并提取出其主分量;然后使用Directionlets提取高空间分辨率的全色图像的空间细节信息,将其"注入"到多光谱图像的主分量中。因此,得到的融合图像具有更多的多光谱图像的光谱信息和全色图像的空间信息。实验结果表明,在UIQI指数、整体图像质量指数Q4、平均梯度等主观视觉效果和客观评价指标上,新方法均优于基于小波变换的方法。The directionlets based on digital segments and integer grids theory can not only inherit the characteristics of dimension-dependable wavelets, but also obtain the flexible multi-directional characteristic by changing the directions of transform and sequences. A novel fusion method for panchromatic and multispectral images based on directionlets transform（DT） and PCA was presented. Firstly, a linear principle component analysis（PCA） was performed on the multispectral images to extract its first principle component, then we used DT to extract the spatial detail information of high-resolution panchromatic image. Therefore, the fused image can carry more spatial and spectral information. Experimental results show the new fusion method has a better performance, such as universal image quality index（UIQI）, unique score index Q4 and average gradient, than wavelet based methods.

关 键 词：图像融合 全色图像 多光谱图像 Directionlets 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]