In this paper, a pixel level multi-resolution image fusion scheme based on wavelet transform is described. In the fusion process, the images are first decomposed based on wavelet transform. Then at each resolution the images are fused. Finally the fused image is obtained by taking the inverse wavelet transform of the fused wavelet coefficients. With the aim of reducing the contrast and structural distortion, when construct each wavelet coefficient for the fused image, we consider not only the corresponding coefficients, but also their close neighbors. Both visual quality (contrast and presence of fine details) and absence of impairments or artifacts are concerned in our method. This approach has been successfully used in image fusion. The experimental results show that the fusion scheme is effectual and the fused images are more suitable for human visual or machine perception.
"Multisensor image fusion based on wavelet transform", Proc. SPIE 4222, Process Control and Inspection for Industry, (10 October 2000); doi: 10.1117/12.403878; https://doi.org/10.1117/12.403878