Multi-focus image fusion using curvature minimization and morphological filtering

Multi-focus image fusion has wide applications in the field of computer vision. This research work presents a two-fold multi-focus image fusion framework in spatial domain. Firstly, the salient features of the focused regions in multi-focus images are detected using Gaussian curvature filter (GCF) and range filtering. The initial focus detection map is then refined using morphological filters. Experiments have shown that the proposed method is fast and robust when compared with latest multi-focus fusion schemes.