Effect of Pre-processing on MST based Infrared and Visible Image Fusion

Abstract

Image fusion combines information from multiple images in a single image to increase the information processing capabilities. Infrared and visible image fusion is finding a lot of applications these days, as it brings complementary information from the source images in one image. The performance of image fusion is affected by noise and artifacts, which tend to creep in during fusion process. Pre-processing of source images is generally done to improve the quality of final fused image. In this paper, a general framework for fusion of infrared and visible image is proposed for investigating role of pre-processing on quality of image fusion. Various arrangements of image enhancement and denoising techniques are used to investigate the role of pre-processing in improving the efficiency of image fusion. The subjective and objective performance evaluations show that joint use of denoising and enhancement improves the performance of infrared and visible image fusion.