Application of multi-focus image fusion in visual power patrol inspection

A multi-focus image fusion (MFIF) framework for visual power patrol inspection is proposed in this paper. The traditional MFIF approaches based on redundant transform need lots of computation cost. In this study, the MFIF technique in dual domain is proposed. The proposed method efficiently captures detail informations of images, and reduce memory usage and computing time. The proposed MFIF method extracts the detail image using M-DirLOTs (multiple directional lapped orthogonal transforms). Firstly, detail image is reconstructed using high-pass subbands. Secondly, MFIF processing in spatial domain is performed. Thirdly, improve the quality of MFIF with mathematical morphology operation. The proposed scheme surmounts some disadvantages of existing MFIF methods in transform domain and spatial domain. Experimental results show that MFIF framework can automatically obtain high quality image in visual inspection.