基于非采样Contourlet变换的图像融合算法

Image Fusion Algorithm Based on Nonsubsampled Contourlet Transform

针对同一场景的红外与可见光图像融合问题,提出了一种基于非采样Contourlet变换的图像融合方法。该方法对图像经非采样Contourlet变换后的低频系数采用基于图像物理特征的"加权平均"融合方法;对于高频系数采用基于局部对比度与空间频率比相结合的系数融合方法。为验证本文算法的有效性,对红外与可见光图像进行了融合实验,实验结果表明该方法相对于传统的简单融合方法以及基于区域能量的融合方法能得到具有更好视觉效果和更优量化指标的融合图像。

For the fusion problem of visible and infrared image of the same scene,a novel image fusion algorithm is proposed based on the nonsubsampled contourlet transform.For choosing the low-frequency coefficients,we propose a weighted average scheme based on the physical features of images.With the high-frequency coefficients,a selection principle is proposed based on region contrast and spatial frequency ratio.In order to verify the effectiveness of proposed algorithm,the experiment upon visible and infrared image are done.The experimental results show that the method compared with the traditional simple fusion method and the regional energy fusion rule can be better in visual quality and objective evaluation criteria.