基于NSCT和分数阶微分的多聚焦图像融合方法

为了增加图像的细节信息，提出了一种基于NSCT和分数阶微分的多聚焦图像融合方法。首先采用NSCT将源图像分解为低频子带和高频子带，低频融合规则以基于局部对比度的变化显著度最大为决策图，高频融合规则以基于分数阶微分算法的梯度最大为决策图。最后通过逆NSCT得到融合图像。通过对比多组融合图像主、客观评价结果表明，该方法能有效保留边缘信息。

Multi-focus Image Fusion Method Based on NSCT and Fractional Differential

In order to improve the details of the image, a multi-focus image fusion method based on NSCT and fractional differential is proposed. Firstly, the source image is decomposed into low-frequency sub-band and high-frequency sub-band by NSCT. The decision graph of low-frequency fusion rule is the maximum significant change based on local contrast, and the decision graph of high-frequency fusion rule is the maximum gradient based on fractional differential algorithm. Finally, the fused image is obtained by inverse NSCT. By comparing the subjective and objective evaluation results of several groups of fused images, it is shown that this method can effectively retain the edge information.