MDLatLRR: A Novel Decomposition Method for Infrared and Visible Image Fusion
Jiangnan University · University of Surrey
Abstract
Image decomposition is crucial for many image processing tasks, as it allows to extract salient features from source images. A good image decomposition method could lead to a better performance, especially in image fusion tasks. We propose a multi-level image decomposition method based on latent low-rank representation(LatLRR), which is called MDLatLRR. This decomposition method is applicable to many image processing fields. In this paper, we focus on the image fusion task. We build a novel image fusion framework based on MDLatLRR which is used to decompose source images into detail parts(salient features) and base parts. A nuclear-norm based fusion strategy is used to fuse the detail parts and the base parts…
Citation impact
- FWCI
- 52.59
- Percentile
- 100%
- References
- 63
Authors
3Topics & keywords
- Image fusion
- Artificial intelligence
- Computer science
- Fuse (electrical)
- Computer vision
- Image processing
- Fusion
- Salient
Funding
- NNNational Natural Science Foundation of ChinaAwards: U1836218, B12018, 61672265, 2017YFC1601800
- MOMinistry of Education of the People's Republic of ChinaAwards: B12018, 111 Project
- HEHigher Education Discipline Innovation ProjectAward: B12018
- DSDefence Science and Technology LaboratoryAward: EP/R018456/1
- MUMultidisciplinary University Research InitiativeAward: EP/R018456/1
- EAEngineering and Physical Sciences Research CouncilAwards: EP/R018456/1, EP/N007743/1, EP/N007743/1, EP/R018456/1
- NKNational Key Research and Development Program of ChinaAward: 2017YFC1601800