针对红外与可见光融合的特点，提出一种基于非下采样Contourlet 变换(NSCT)和区域能量判断的图像融合方法。利用NSCT 变换对两原图像进行分解，得到一个低频子图像和多个不同方向的高频子图像，对低频子带采用最大值的方法进行融合，而高频子带先计算各个系数的区域能量匹配度，再计算判断阈值。当高频系数中各点的匹配度大于阈值时，采用区域能量加权融合方法；当对应点的匹配度小于阈值时，采用区域能量最大值的方法进行融合，通过NSCT 逆变换获得融合图像。该方法的特点是算法简单，阈值选取具有自适应性。实验结果表明该方法能够取得较好的视觉效果和量化数据，相比于其他基于NSCT 的融合方法，熵值提高了0.5%~6.8%，空间频率提高了1%~13%，标准方差提高了0~24.1%，是一种简单有效的融合方法。

A fusion method for infrared and visual images based on local energy and non-subsampled Contourlet transform (NSCT) is proposed. The two original images are decomposed into a low frequency subband image and a few high frequency subband images by NSCT. The maximum selection rule is used to fuse the low frequency subband and the high frequency subbands are merged with local energy match degree. The match degree of the two corresponding local energy in high frequency subbands is computed and the match degree threshold is obtained, if the match degree is less than threshold, the maximum of local energy is used to fuse the high frequency subbands, otherwise, the weighted local energy is used to fuse high frequency subbands. The fused image using the inverse transform of NSCT is reconstructed. The experimental results show that fusion method can get better visual effect and preserve image detail information of original image. Comparing with other fusion methods based on NSCT, the entropy is increased by 0.5%~6.8% , the space frequency is increased by 1% ~13% and the standard deviation is increased by 0~24.1%, it is an effective and simple fusion method.