An optimized block-based intuitionistic fuzzy framework for multi-focus image fusion

Abstract

Introduction Multi-focus image fusion aims to generate a single all-in-focus image by combining multiple images captured at different focal depths. However, accurately identifying focused and blurred regions remains challenging due to real-world focus transitions and the uncertainties inherent between sharp and defocused areas. Methods To address these limitations, this article presents a new multi-focus image fusion method employing a novel intuitionistic fuzzy generator. In the proposed framework, an input image is initially converted into an intuitionistic fuzzy image (IFI), followed by a fusion rule termed the optimized block-based partitioning and defocusing synthesis algorithm to generate the final fused image. The utilization of IFIs facilitates the management of uncertainties associated with the membership and non-membership degrees of an image. Results The proposed fusion algorithm demonstrates superior performance compared with existing state-of-the-art methods in terms of entropy, average gradient, and spatial frequency. Discussion Analytical experiments and comparative evaluations demonstrate that the proposed approach achieves improved visual quality and effectively addresses the uncertainties associated with focused and defocused regions in multi-focus image fusion.