Comparison of fusion methods for the infrared and color visible images

Abstract

Image fusion involves merging two or more images in such a way as to retain the most desirable characteristics of each. When a color visible image is fused with infrared image, the desired result is a color image with natural color appearance and full information. In this paper, three image fusion algorithms based on discrete wavelet transform (DWT), dual-tree complex wavelet transform (DT-CWT) with image enhancement and bidimensional empirical model decomposition (BEMD) are compared for the infrared and color visible images. A novel image quality metric is proposed to evaluating the performance of image fusion algorithms. This measurement is defined for comparative performance analysis and is used on the output of fusion algorithms that have been applied to a set of infrared and color visible band imagery.