基于NSST和稀疏表示的多聚焦图像融合方法

Mul-focusimage fusion based on NSST and sparse representation

为使融合图像保留丰富的细节和纹理信息,提出了一种基于非下采样剪切波变换(NSST)和稀疏表示的多聚焦图像融合方法。鉴于稀疏表示能够有效地捕捉图像中的结构信息这一优势,并充分考虑像素间的区域相关性,低频子带系数采用稀疏表示和区域能量相结合的融合策略,以及加权平均的融合规则,高频子带系数采用区域能量取大的融合规则。实验结果表明,该方法融合图像清晰度高,能够更好地保留图像细节信息。

In order to make the fused image retain rich detail and texture information,,a multi-focus image fusion method based on non-downsampled shear wave transform(NSST)and sparse representation is proposed.In view of the advantage that sparse representation can effectively capture structural information in the image,and fully consider the regional correlation between pixels,the low-frequency subband coefficients adopt a fusion strategy combining sparse representation and regional energy,as well as a fusion rule of weighted average,and the high-frequency subband coefficients adopt a fusion rule that increases the regional energy.Experimental results show that the method has high fused image clarity and can better preserve image details.