基于小波变换和CSF的图像融合方法

An image fusion method based on the DWT and CSF

将HVS模型的CSF用于像素层图像融合中是一种新的方法。首先,将源图像进行一层的二维离散小波分解,得到近似系数和细节系数;其次,近似部分采用加权平均方法,细节部分采用CSF滤波方法,来得到融合后的小波系数;最后,将得到的小波系数进行逆小波变换,即得最后的融合图像。此方法计算量小,融合图像符合人类视觉系统,可应用于工程实践中。

It is a novel method that the CSF of the HVS model is applied to pixel-level image fusion. First, the source images are decomposed into an approximate coefficient and three detail coefficients by the DWT respectively. Secondly, the fused approximate coefficient is obtained by averaging the approximate coefficients of the source images and the fused detail coefficients are obtained by CSF filter. Finally, the fused image is obtained by inverse wavelet transform. This method requires much less computation and makes the fused images accord with the human visual system. So, it can be applied to engineering.