基于改进型NSCT 变换的灰度可见光与红外图像融合方法

针对灰度可见光与红外图像融合,提出一种基于改进型非下采样轮廓波变换(NSCT)的图像融合方法.不同于经典NSCT模型,改进型NSCT变换摈弃了细节捕捉能力不强的非下采样金字塔分解机制,采用冗余提升不可分离小波变换实现对源图像的多尺度分解;然后,分别采用基于区域平均能量匹配度、邻域系数差和信息熵的融合规则,得到融合图像的低频系数和高频系数;最后,通过改进型NSCT逆变换得到了融合图像.实验结果验证了该方法的有效性.

Fusion method for gray-scale visible light and infrared images based on improved NSCT

Abstract: To the fusion of gray-scale visible light and infrared images, an image fusion method based on improved nonsubsampled
contourlet transform(NSCT) is proposed. Unlike the classic NSCT model, the improved NSCT substitutes
redundant lifting non-separable wavelet(RLNSW) for the former NSP decomposition mechanism whose performance of
capturing the detail information is not good to realize the multi-scale decomposition of the source images. Then, the lowfrequency
coefficients and high-frequency coefficients for the fused image can be obtained by means of the fusion rule based
on region mean energy matching degree, neighborhood coefficient deviation and information entropy, respectively. Finally,
the fused image is reconstructed by the inverse improved NSCT. Experimental results show the effectiveness of the proposed
method.