Journal
NEURAL PROCESSING LETTERS
Volume 54, Issue 5, Pages 3551-3564Publisher
SPRINGER
DOI: 10.1007/s11063-020-10316-6
Keywords
Reflectance field estimation; Sparse representation; Illumination preprocessing; Pattern recognition
Categories
Funding
- National Natural Science Foundation of China [61873106]
- National Nature Science Foundation of Jiangsu Province [BK20171264]
- Jiangsu Qing Lan Project to Cultivate Middle-aged and Young Science Leaders
- Jiangsu Six Talent Peak Project [XYDXX-047, XYDXX-140]
- University Science Research General Research General Project of Jiangsu Province [18KJB520005, 19KJB520004]
- Innovation Fund Project for Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education [JYB201609]
- Lianyungang Hai Yan Plan [2018-ZD003, 2018 -QD-001, 2018-QD-012]
- Science and Technology Project of Lianyungang High-tech Zone [ZD201910, ZD201912]
- Natural Science Foundation Project of Huaihai Institute of Technology [Z2017005]
Ask authors/readers for more resources
The study introduces a unified framework for face image illumination preprocessing and recognition, proposing a JRSR method for face recognition under extreme lighting conditions. The method effectively separates the identity factor and interfered illumination, improving recognition accuracy and preprocessing efficiency.
Illumination preprocessing is an important ingredient for handling lighting variation face recognition challenge. Nonetheless, existing methods are usually designed to be independent of the face recognition methods and the interaction between them is not yet well explored. In this paper, we formulate the face image illumination preprocessing and recognition into a unified sparse representation framework and propose a novel joint reflectance field estimation and sparse representation (JRSR) method for face recognition under extreme lighting conditions. The proposed method separates the identify factor and the interfered illumination of a query sample simultaneously by one nonconvex sparse optimizing model. We also present an efficient approximation algorithm to solve JRSR in this paper. Evaluation on several face databases and the experimental results of face recognition with illumination variation clearly demonstrate the advantages of our proposed JRSR algorithm in illumination preprocessing efficiency and recognition accuracy.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available