混合多尺度分析和改进PCNN相结合的图像融合方法

为了更好地融合全色图像中的空间细节信息和多光谱图像中的光谱信息,提出一种基于混合多尺度分析和改进脉冲耦合神经网络(PCNN)的多光谱与全色图像融合方法.首先对全色图像和多光谱图像进行非下采样剪切波变换(NSST),并结合不同多尺度分析方法的互补特性,利用平稳小波变换(SWT)对低频分量部分进行二次分解,在混合多尺度域进行系数融合及SWT逆变换;然后采用基于PCNN的融合规则对高频分量部分进行融合;最后对融合后的高低频系数进行NSST逆变换,得到融合图像.在2组卫星拍摄的多光谱和全色图像上的实验结果表明,在主观视觉与客观评价指标的总体效果上,该方法优于其他8种经典以及流行方法.

Image Fusion Method Using Multi-scale Analysis and Improved PCNN

In order to effectively combine the spectral information of the multispectral (MS) image with spatial detail information of the panchromatic (PAN) image, a new fusion method of the MS and PAN images based on multi-scale analysis and improved pulse coupled neural network (PCNN) is proposed. The PAN and MS images are decomposed by non-subsampled shearlet transform (NSST) to obtain the high and low frequency coefficients firstly, then the unique characteristic of different multi-scale analysis methods is performed to design the fusion rule of the low frequency coefficients which are decomposed again with stationary wavelet transform (SWT) and fused in multi-scale domain;for the fusion of the high frequency coefficients, improved PCNN based fusion rule is designed to enhance the image details;finally, the fused high and low frequency coefficients are reconstructed with the inverse NSST. Experimental results show that the proposed method is superior to the other eight traditional and popular fusion methods from the overall effect of the visual aspects and the objective parameters.