Boosting Wavelet-Based Image Fusion Using Equal Weighted Average of DSIHE and CLAHE

Image fusion remains fundamental in diverse technical domains such as computer vision, remote sensing, medical imaging, and military applications. With the rapid evolution of technology, the significance of image fusion in research is escalating steadily. Image fusion is paramount across multiple fields as it amalgamates data from numerous images or imaging modalities, creating a unified composite image. Wavelet image fusion is a technique specifically designed to combine information sourced from multiple images at various scales and resolutions. This methodology harnesses the power of wavelet transform, a mathematical tool, to achieve this fusion. Wavelet image fusion finds extensive applications in sectors like remote sensing, medical imaging, computer vision, and surveillance, where amalgamating data from diverse sources is pivotal for decision-making, analysis, and visualization. However, it's important to note that wavelet-based image fusion, while powerful, could be more flawless. It can introduce undesirable artifacts such as ringing and blurring effects in the resulting fused images. To address these limitations, a novel approach has been proposed. This method aims to mitigate blurring effects by employing Wavelet fusion of Dualistic Sub Image Histogram Equalization (DSIHE) and Clipped Limited Adaptive Histogram Equalization (CLAHE). Experimental results were obtained from analyzing datasets, including the Multi-focus Image Dataset Lytro Multifocus Images Dataset, using performance metrics like entropy, NIQE, and BRISQUE from which Naturalness Image Quality Evaluator (NIQE) demonstrates the superior effectiveness of the proposed method.