ISSN 2231-2307, Volume-2, Issue-4, September 2012 Improved.pdfVIP

International Journal of Soft Computing and Engineering (IJSCE) ISSN: 2231-2307, Volume-2, Issue-4, September 2012 Improved Block Based Feature Level Image Fusion Technique Using Multiwavelet with Neural Network C.M.Sheela Rani, V.VijayaKumar, B.V.Ramana Reddy 飥 PAN image and the colour information of the MS image. Abstract鈥擨mage fusion is defined as the process of combining Hence, the fused image is a high-resolution MS image. two or more different images into a new single image retaining the The fused image should have few following requirements - important features from each image with extended information it should preserve all relevant information contained in the content. To overcome the spectral distortions in the fused image, input images and it should not introduce any artefacts or many multiresolution based approaches have been proposed. They inconsistencies. A straightforward approach is to compute include different pyramid transforms and discrete scalar wavelet the average of all the pixel values to generate a fused image. transforms. The multiwavelet transform (MWT) produces a non-redundant image representation, which provides better Even though this approach is simple, the low contrast of the spatial and spectral localization of image formation. This paper fused image seriously limits its usage. To overcome this has derived an efficient b