A wavelet-based scene image fusion algorithm

A pixel level image fusion algorithm based on wavelet transform using multi fusion rules for merging scene images is proposed. The two source images are first decomposed using the discrete wavelet transform. Couples of high frequency details of wavelet coefficients are then merged according to the salient features. Meanwhile the gross approximations of the images at the coarsest resolution level are combined together according to their similarity. The fused image is reconstructed by performing the inverse wavelet transform from the combined coefficients. Experimental results show that the proposed approach can eliminate the effect of the bad weather conditions on the scene images.