针对红外与可见光图像特点, 提出一种基于非下采样Contourlet变换(NSCT)的红外与可见光图像融合算法。该算法对源图像进行NSCT分解, 得到低频分量和各带通方向子带分量；引入图像区域相关系数决策度, 对低频分量和带通方向子带分量采用不同的融合规则进行融合；最后经过NSCT逆变换得到融合图像。实验证明, 该方法可以更好地保留目标信息和图像细节信息。

Aiming at the features of infrared and visible images a fusion algorithm based on Nonsubsampled Contourlet Transform (NSCT) was proposed for fusion of infrared and visible images. Firstly the original images were decomposed by using NSCT then the low frequency coefficients and high frequency coefficients were obtained. The correlation coefficient decision of the image area was introduced and different fusion rules were used for fusion of low frequency components and bandpass sub-band components. The final fused image was obtained after NSCT inverse transformation. The experiments proves that this method can better keep the target information and image details.