基于NSCT的红外与可见光图像融合

针对红外与可见光图像的不同特点，提出一种基于非采样Contourlet变换（NSCT）的红外与可见光图像融合算法。采用NSCT对源图像进行多尺度、多方向分解；分别采用基于局部能量和区域特征的融合规则得到融合图像的低频子带系数和带通方向子带系数；最后经过NSCT逆变换得到融合图像。实验结果表明，该算法能够获得较理想的融合图像，其融合效果优于基于Contourlet变换的图像融合算法。

Fusion of infrared and visible images based on nonsubsampled Contourlet transform

Aiming at the features of infrared and visible images,a fusion algorithm based on NonSubsampled Contourlet Transform（NSCT） is proposed for infrared and visible image fusion.Firstly,the NSCT is used to perform the multiscale and multidirection decomposition of the source images.Secondly,low frequency subband coefficients and bandpass directional subband coefficients of the fused image can be obtained by the fusion rules based on region energy and area character,respectively.Finally,the fused image is reconstructed by performing the inverse NSCT on the combined coefficients.Simulation experiments show that this algorithm can yield fusion image with better fusion result than that of using Contourlet transform.