CASIA OpenIR  > 模式识别国家重点实验室  > 图像与视频分析
Learning Robust Face Representation With Classwise Block-Diagonal Structure
Li, Yong; Liu, Jing; Lu, Hanqing; Ma, Songde
Source PublicationIEEE Transactions on Information Forensics and Security
2014-12-01
Volume9Issue:12Pages:2051-2062
SubtypeArticle
AbstractFace recognition has been widely studied due to its importance in various applications. However, the case that both training images and testing images are corrupted is not well solved. To address such a problem, this paper proposes a semisupervised learning algorithm for robust face recognition. In particular, we consider three items in the proposed formulation. First, a low-rank and sparse representation for face recognition is required to handle the possible contamination of the whole data. Second, a classwise block-diagonal structure of the learned representation is expected to promote discrimination among different classes. With the structure regularization, we make the samples from different classes be reconstructed with different bases as much as possible. Third, a compact and discriminative dictionary should be learnt to handle the problem of corrupted data. Extensive experiments on three public databases are performed to validate the effectiveness of our approach. The strong identification capability of representation with block-diagonal structure is verified.
KeywordRobust Face Recognition Low-rank And Sparse Representation Classwise Block-diagonal Structure
WOS HeadingsScience & Technology ; Technology
WOS KeywordRANK MATRIX RECOVERY ; SPARSE REPRESENTATION ; IMAGE CLASSIFICATION ; LINEAR-SUBSPACES ; RECOGNITION ; DICTIONARY ; ALGORITHM ; MODELS
Indexed BySCI
Language英语
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS IDWOS:000353289900004
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/8109
Collection模式识别国家重点实验室_图像与视频分析
AffiliationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Li, Yong,Liu, Jing,Lu, Hanqing,et al. Learning Robust Face Representation With Classwise Block-Diagonal Structure[J]. IEEE Transactions on Information Forensics and Security,2014,9(12):2051-2062.
APA Li, Yong,Liu, Jing,Lu, Hanqing,&Ma, Songde.(2014).Learning Robust Face Representation With Classwise Block-Diagonal Structure.IEEE Transactions on Information Forensics and Security,9(12),2051-2062.
MLA Li, Yong,et al."Learning Robust Face Representation With Classwise Block-Diagonal Structure".IEEE Transactions on Information Forensics and Security 9.12(2014):2051-2062.
Files in This Item: Download All
File Name/Size DocType Version Access License
Learning Robust Face(2662KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li, Yong]'s Articles
[Liu, Jing]'s Articles
[Lu, Hanqing]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li, Yong]'s Articles
[Liu, Jing]'s Articles
[Lu, Hanqing]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li, Yong]'s Articles
[Liu, Jing]'s Articles
[Lu, Hanqing]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Learning Robust Face Representation With classwise block-diagonal structure.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.