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.