MULTISENSOR IMAGE FUSION USING THE WAVELET TRANSFORM

The goal of image fusion is to integrate complementary information fro m multisensor data such that the new images are more suitable for the purpose of human visual perception and computer-processing tasks such as segmentation, feature extraction, and object recognition. This pape r presents an image fusion scheme which is based on the wavelet transf orm. The wavelet transforms of the input images are appropriately comb ined, and the new image is obtained by taking the inverse wavelet tran sform of the fused wavelet coefficients. An area-based maximum selecti on rule and a consistency verification step are used for feature selec tion. The proposed scheme performs better than the Laplacian pyramid-b ased methods due to the compactness, directional selectivity, and orth ogonality of the wavelet transform. A performance measure using specia lly generated test images is suggested and is used in the evaluation o f different fusion methods, and in comparing the merits of different w avelet transform kernels. Extensive experimental results including the fusion of multifocus images, Landsat and Spot images, Landsat and Sea sat SAR images, IR and visible images, and MRI and PET images are pres ented in the paper. (C) 1995 Academic Press, Inc.