中文摘要：

分析了非子采样Contourlet变换滤波器组的设计与实现方法，提出一种基于非子采样Contourlet变换的红外与可见光图像融合算法。首先将图像作非子采样拉普拉斯金字塔尺度分解，并在各个尺度层对高频子带作非子采样方向分解；然后分别采用基于区域能量和区域方差的的融合规则得到融合图像的非子采样Contourlet低频系数和高频系数；最后再进行非子采样Contourlet逆变换得到融合图像。实验结果表明，该方法的融合效果优于a trous小波变换方法和Contourlet变换方法。

英文摘要：

An image fusion algorithm of infrared and visible light images based on the nonsubsampled Contoutlet transform （NSCT） is proposed by analyzing the design and implementation of the filter bands of the NSCT. Firstly, multiscale decomposition of the source images is performed with nonsubsampled Laplacian pyramid. Directional decomposition of the high-frequency subbands in every scale is also done with nonsubsampled directional filter bands. And then, the low-frequency coefficients and high-frequency coefficients for the fused image can be obtained by means of the fusion rule based on region variance and local energy, respectively. Finally, the fused image is reconstructed by the inverse NSCT. Experimental results show that the method presented works better than the a trous wavelet transform and the Contourlet transform.