基于NSST的红外与可见光图像融合算法

针对红外与可见光图像具有不同的特点，提出一种新的基于非下采样剪切波变换（NSST）的红外与可见光图像融合算法.算法首先采用NSST将已配准的红外与可见光图像进行分解，得到低频子带图像和各尺度各方向的高频子带图像；然后对低频子带图像采用一种基于显著图的低频融合规则进行融合，而对高频子带图像的融合，结合人眼视觉特性，采用一种基于改进的区域对比度的融合规则；最后，对融合的低频子带图像和高频子带图像进行NSST逆变换得到融合图像.实验结果表明，该算法能够有效地综合红外与可见光图像中的重要信息，融合效果要优于一般的基于NSCT、NSST的图像融合方法.

Research on the Fusion Algorithm of Infrared and Visible Images Based on Non-subsampled Shearlet Transform

Aiming at the different features between infrared imagery and visible images,a new fusion algorithm of infrared imagery and visible image based on Non-subsampled Shearlet Transform (NSST) is proposed.Firstly the algorithm decomposes infrared and visible light image that have been registered by NSST,getting the low-frequency subband images and the scale of each direction high frequency subband images;Then the low frequency subband images use a low frequency fusion rules based on the significant figure,and combined with human visual characteristic,high frequency subband image adopt a fusion rules of improving regional contrast;Finally,get fusion image by making NSST inverse transformation for the fusion of low frequency subband image and high frequency subband images.Experimental results show that the proposed algorithm can effectively synthesize the important information of infrared and visible images,and the fusion effect is better than that of the general image fusion method based on NSCT and NSST.