Multi-focus image fusion based on non-negative sparse representation and patch-level consistency rectification

作者：

Highlights：

• A CNNSR model is introduced for multi-focus image fusion.

• Local consistency among adjacent patches is considered in the fusion method.

• A compact non-negative dictionary with small number of atoms is constructed.

• A patch-level consistency rectification strategy during the fusion process is proposed to reduce the spatial artifacts.

• The fusion method has high computation efficiency.

摘要

•A CNNSR model is introduced for multi-focus image fusion.•Local consistency among adjacent patches is considered in the fusion method.•A compact non-negative dictionary with small number of atoms is constructed.•A patch-level consistency rectification strategy during the fusion process is proposed to reduce the spatial artifacts.•The fusion method has high computation efficiency.

论文关键词：Multi-focus image fusion,Non-negative sparse representation,Compact non-negative dictionary construction,Patch-level consistency rectification,High computational efficiency

论文评审过程：Received 30 November 2018, Revised 4 December 2019, Accepted 8 March 2020, Available online 9 March 2020, Version of Record 16 March 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107325