Multi-Spectral Image Fusion Using Wavelet Transform

Abstract

The fusion of visible and infrared images of the same scene results in a single fused image that can provide a more detailed interpretation of the situation. With the help of energy compression and multiresolution characteristics of wavelets, which fuse the salient features such as edges and textures from source images without introducing any artifacts for context improvement and situational awareness, image fusion is more effective. This paper combines visible and infrared images (LWIR and NIR) using different wavelet transform methods on night-time imagery up to the 8th level of image decomposition. The performance of various wavelet techniques for multi-spectral image fusion was evaluated based on subjective and objective parameters. Additionally, Petrovic Metric parameters are used to measure the fusion performance.