Exploring a unified low rank representation for multi-focus image fusion

作者：

Highlights：

• The spatial consistency among the local regions is considered to reduce the spatial artifacts.

• A unified low-rank representation (ULRR) model is proposed.

• The proposed fusion method is implemented super-pixel by super-pixel.

• The fusion method outperforms than the existing fusion methods by a clear margin.

摘要

•The spatial consistency among the local regions is considered to reduce the spatial artifacts.•A unified low-rank representation (ULRR) model is proposed.•The proposed fusion method is implemented super-pixel by super-pixel.•The fusion method outperforms than the existing fusion methods by a clear margin.

论文关键词：Multi-focus image fusion,Super-pixel clustering,Unified low-rank representation,Spatial consistency

论文评审过程：Received 3 October 2019, Revised 19 August 2020, Accepted 7 November 2020, Available online 13 November 2020, Version of Record 19 February 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107752