基于NSCT变换和小波变换相结合的图像融合算法研究

Image Fusion Algorithms by Combining NSCT and Wavelet Transform

针对小波变换在表达图像边界及线状特征上的缺陷,以及NSCT变换在表达图像细节信息的不足,提出了在红外图像与可见光图像融合的过程中采用基于NSCT变换和小波变换相结合的图像融合算法。在图像NSCT分解后,对低频系数使用基于小波变换的融合算法,对高频系数结合融合图像的特点采用了基于区域方差的融合规则。实验结果表明,基于NSCT变换和小波变换相结合的融合算法能更好地保持可见光图像的光谱信息和红外图像的目标信息,具有更多的细节特征以及更清晰的边缘。

An image fusion algorithm is proposed combining NSCT transform and wavelet transform in the fusion of infrared image and visible image,targeting solving the defects of boundary expression,linear features and information lack of details in NSCT transform.After NSCT,awvelet transform image fusion algorithm is adopted for low frequency coefficient while a fusion rule based on regional variances is used to fuse the high frequency coefficients by the the characteristics of the image.Experimental results show that the fusion algorithm can preserve the spectral information of visible image and target information of infrared image better than any single transform,obtaining more detailed features and sharper edge.