基于NSCT变换的红外与可见光图像融合新算法
A novel fusion method of infrared and visible images based on NSCT

考虑红外与可见光图像的成像机理，提出把非下采样Contourlet变换用于该类图像融合的改进措施. 先用NSCT变换在多尺度和多方向上去分解已经配准的图像，可以得到低频系数部分和高频系数部分；再对低频子代部分应用归一化局部方差的差和融合阈值比较的融合规则，对于高频方向子代部分则使用拉普拉斯能量和的能量取大的融合方法；最后把NSCT逆变换应用在高低频部分，输出最后的图像. 通过对比实验可知，提出的新方法较传统的图像融合方法更能准确地反映所要研究的场景.
Considering the imaging mechanism of infrared and visible images，an improved measure of infrared and visible images based on NSCT was proposed in the paper. Firstly， theregistered images are decomposed into low frequency coefficients part and high frequency coefficients part at multi-scale and multi-direction by using NSCT. Then the fusion rule based on comparing the subtraction of normalized regional variance with threshold is used in the low frequency subband part. The fusion method based on maximum energy of sum of Laplace energy is used in the high frequency directional subbandspart. Finally，the ultimate new image is output after inverse NSCT dealed with high frequency and low frequency part. The contrast experiment showed the proposed method is more accurate for reflecting the study scene than traditional image fusion methods