Abstract: State-of-the-art remote sensing image fusion methods based on component-substitution framework model have difficulty to preserve the spectrum characteristics and spatial resolution at the same time.In this paper,a remote sensing image fusion method based on regional correlation of the images is proposed.A novel pulse coupled neural network is proposed for image segmentation based on the difference of local correlation between the panchromatic image and the multispectral image,while the fusion rules are determined by the differences in regional correlation.The experimental results show that the proposed method performs very well for the remote sensing image fusion.