Multi-Focus Image Fusion: A Systematic Literature Review

Multi-Focus Image Fusion (MFIF) was designed to solve the issue of the limited depth of field inherent in the optical lens of imaging systems. In addition, MFIF extracts all the relevant information from the source image. In this study, we present a systematic review of the current literature to identify and discuss the main requirements and features of MFIF. A systematic literature review was conducted using The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology and 550 articles were extracted from the Springer, Science Direct, and IEEE databases. Based on the extracted data, 74 studies were selected according to the inclusion and exclusion criteria. The findings are presented in four subsections that discuss the most frequently employed fusion methods, activity level measurements, publicly available image datasets, and evaluation indicators used to judge the quality aspect of a fused image in MFIF. According to the results, deep learning methods are preferred as fusion methods, while spatial frequency is the most popular technique for measuring activity levels. Most studies include image feature-based evaluation indicators in addition to the Lytro dataset as input to test the efficacy of the fusion method. There is growing interest in MFIF, but limited literature is available on boundary region fusion methods and novel activity level measurements. Finally, several potential research areas and prospects are identified in the review. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.