Ensemble-Inspired Multi-focus Image Fusion Framework

Machine learning algorithms are quite extensively used in the diverse signal and image processing applications. In this paper, a new multi-focus image fusion method at feature level is proposed which is inspired by ensemble learning. The fusion rule is based on two separate models which are trained on the same dataset and an ensemble of them is considered to give the final fusion result. For training the models, four different feature maps are defined, each mapping brings out distinct features from the input images. Upon considerable experimentation, the fused images obtained gave superior and visually appealing results as compared to the other state-of-the-art techniques. � 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.