Research On Image Fusion Method Based On NSCT

Image fusion belongs to an important form of information fusion.It extracts and retains the multi-source sensor images obtained from different perspectives.Image fusion can also provide effective information for further processing such as image segmentation,target detection and recognition.At present,image fusion technology has been widely used in medical research,remote sensing processing,intelligent creation and other fields.In this paper,multi-scale analysis tools are used to study multi-source image fusion methods.By analyzing two kinds of image sources,remote sensing image and false color image,a fusion method of remote sensing image and false color image method is proposed.The main contents of this paper are as follows:On one hand,based on the NSCT-based remote sensing image fusion method,the fusion of SAR image and panchromatic image method is proposed.According to the idea of regional segmentation,the combination of weighted edge retention and regional mean square error is adopted as the fusion rule.The SAR image is divided and the fusion coefficient is selected.The simulation results show that this method not only preserves the spatial resolution of the panchromatic image,but also effectively adds the target information of the SAR image.On the other hand,based on the NSCT-based false color image fusion method,the NSCT image fusion technology and color display technology are combined.The fusion rule based on the combination of regional variance adaptive weighting method and the maximum energy and maximum horizontal gradient method are adopted.Then,the relational images between the two source images and the fused image are calculated by intersection and inverse filtering,and sent to the RGB channels to get color fusion images respectively.The simulation results show that the method finally get the image is more abundant on color,and the edge of the outline of each area block is clearer,further increases the difference between the target and the background.