Multi-focus image fusion with a deep convolutional neural network

详细信息    查看全文

• 作者：Yu Liu^a ; ^{yuliu@hfut.edu.cn} ; ^{liuyu1@mail.ustc.edu.cn} ; Xun Chen ; ^a ; ^{xun.chen@hfut.edu.cn} ; Hu Peng^a ; Zengfu Wang^b
• 关键词：Image fusion ; Multi-focus image fusion ; Deep learning ; Convolutional neural networks ; Activity level measurement ; Fusion rule
• 刊名：Information Fusion
• 出版年：2017
• 出版时间：July 2017
• 年：2017
• 卷：36
• 期：Complete
• 页码：191-207
• 全文大小：5850 K
• 卷排序：36

文摘

Introduces Convolutional neural networks (CNNs) into the field of image fusion. Discusses the feasibility and superiority of CNNs used for image fusion. Proposes a state-of-the-art CNN-based multi-focus image fusion method. Exhibits the potential of CNNs for other-type image fusion issues. Puts forward some suggestions on the future study of CNN-based image fusion.