Abstract: Pansharpening combines a low-resolution color multispectral image with a high-resolution grayscale panchromatic image. Multiresolution image fusion is an algorithmic approach to combine a PAN image with MS image. It combines the clear geometric features of the panchromatic image and the color information of the multispectral image. The objective of this fusion process is to enhance the spatial resolution of the multispectral images to make important features more apparent for human or machine perception. This enhancement is performed by injecting the high frequency component of the panchromatic image into the lower resolution ones without deteriorating the spectral component in the fused product. Here, gravitational search based image fusion technique is used. The fused image is essentially constructed by using the properties of panchromatic and multispectral images within a window to determine the weighting factors of the input images. To obtain accurate edge details, edge detector is used to locate the edge pixels in the initial estimate and gives better edge details in the final solution. Experimental results show the effectiveness of the proposed method.
Keywords: PAN, MS, Pansharpening, GSA.