Improving Wavelet-Based Image Fusion with Weighted Average of High Boost and CLAHE

Image fusion continues to be essential across various domains, such as computer vision, remote sensing, medical imaging, and military applications, from a technical standpoint. Given the rapid advancements in technology, The significance of image fusion in research is steadily increasing on a daily basis from a technical perspective. In various fields, image fusion plays a crucial role by integrating information from multiple images or imaging modalities into a unified composite image. The technique of wavelet-based image fusion is employed to merge multiple images or sources of images at varying scales and resolutions. Wavelet-based image fusion is a technique utilized to amalgamate multiple images or image sources at different scales and resolutions. It leverages the mathematical tool called wavelet transform to achieve this. The application of wavelet-based image fusion is prevalent in diverse fields like remote sensing, medical imaging, computer vision, and surveillance. This technique is vital in these domains as it enables the integration of information from multiple sources, facilitating decision-making, analysis, and visualization processes. Wavelet-based image fusion, while a powerful technique, has its limitations. The method can introduce artefacts like ringing and blurring effects in the fused output images. The proposed method removes the blurring effects using Wavelet fusion of the Weighted High-Boost Filters (HBF) and Weighted Clipped Limited Adaptive Histogram Equalization (CLAHE). The Results of experimentation on the Medical Images Dataset and IR and Visible Images Dataset using performance metrics alias entropy, NIQE, and BRISQUE have proven the proposed method to be better.