Multi-focus image fusion based on joint sparse representation and optimum theory

作者：

Highlights：

• Joint sparse representation is adopted to depart source images into complementary sub-images and one redundant sub-image.

• Regardless of the redundant sub-image, the only thing we need do is to try to fuse two complementary sub-images.

• One fusion rule of sparse coefficients is proposed, which is based on the optimum theory and solved by OMP method.

• By adding the fused complementary sub-image and redundant sub-image together, the fused image in all-focus can be obtained.

摘要

•Joint sparse representation is adopted to depart source images into complementary sub-images and one redundant sub-image.•Regardless of the redundant sub-image, the only thing we need do is to try to fuse two complementary sub-images.•One fusion rule of sparse coefficients is proposed, which is based on the optimum theory and solved by OMP method.•By adding the fused complementary sub-image and redundant sub-image together, the fused image in all-focus can be obtained.

论文关键词：Joint sparse representation,Optimum theory,Orthogonal matching pursuit,Multi-focus image fusion

论文评审过程：Received 15 April 2019, Revised 27 May 2019, Accepted 9 June 2019, Available online 19 June 2019, Version of Record 28 June 2019.

论文官网地址：https://doi.org/10.1016/j.image.2019.06.002