Multifocus Image Fusion based on Pixel Significance using Biorthogonal Wavelets

Image fusion is gaining momentum in the research community with the aim of combining all the important information from multiple images such that the fused image contains more accurate and comprehensive information than that contained in the individual input images. In this paper, it is proposed to fuse multifocus images to get 'all-in-focus' in the wavelet domain using biorthogonal wavelets. To compute fused pixel value, weighted average of the source pixels is taken, where the weight to be given to the pixel is adaptively decided by establishing parent-child relationship among the pixels at different levels of multiresolution decomposition. Two important properties wavelet symmetry and linear phase of biorthogonal wavelets have been exploited for image fusion because they are capable to preserve edge information and hence reducing the distortions in the fused image. The performance of the proposed method have been extensively tested on several pairs of multifocus images and also compared quantitatively with five recently proposed methods with the help of well-known parameters including Petrovic parameters. Results show that the major achievement of this work is that it significantly increases the quality of the fused image, both visually and in terms of standard Petrovic parameters.