OPT OpenIR  > 光谱成像技术研究室
Integrating Conventional and Inverse Representation for Face Recognition
Xu, Yong1; Li, Xuelong2; Yang, Jian3; Lai, Zhihui1; Zhang, David4
作者部门光学影像学习与分析中心
2014-10-01
发表期刊IEEE TRANSACTIONS ON CYBERNETICS
ISSN2168-2267
卷号44期号:10页码:1738-1746
摘要Representation-based classification methods are all constructed on the basis of the conventional representation, which first expresses the test sample as a linear combination of the training samples and then exploits the deviation between the test sample and the expression result of every class to perform classification. However, this deviation does not always well reflect the difference between the test sample and each class. With this paper, we propose a novel representation-based classification method for face recognition. This method integrates conventional and the inverse representation-based classification for better recognizing the face. It first produces conventional representation of the test sample, i.e., uses a linear combination of the training samples to represent the test sample. Then it obtains the inverse representation, i.e., provides an approximation representation of each training sample of a subject by exploiting the test sample and training samples of the other subjects. Finally, the proposed method exploits the conventional and inverse representation to generate two kinds of scores of the test sample with respect to each class and combines them to recognize the face. The paper shows the theoretical foundation and rationale of the proposed method. Moreover, this paper for the first time shows that a basic nature of the human face, i.e., the symmetry of the face can be exploited to generate new training and test samples. As these new samples really reflect some possible appearance of the face, the use of them will enable us to obtain higher accuracy. The experiments show that the proposed conventional and inverse representation-based linear regression classification (CIRLRC), an improvement to linear regression classification (LRC), can obtain very high accuracy and greatly outperforms the naive LRC and other state-of-the-art conventional representation based face recognition methods. The accuracy of CIRLRC can be 10% greater than that of LRC.
文章类型Article
关键词Face Recognition Pattern Recognition Representation-based Classification
WOS标题词Science & Technology ; Technology
DOI10.1109/TCYB.2013.2293391
收录类别SCI ; EI
关键词[WOS]TOTAL LEAST-SQUARES ; SPARSE REPRESENTATION ; FEATURE-EXTRACTION ; IMAGE ; CLASSIFICATION ; INFORMATION ; SELECTION ; SYMMETRY ; DOMAIN ; SHAPE
语种英语
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号WOS:000342228100003
引用统计
被引频次:120[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.opt.ac.cn/handle/181661/22368
专题光谱成像技术研究室
作者单位1.Harbin Inst Technol, Shenzhen Grad Sch, Biocomp Res Ctr, Shenzhen 518055, Guangdong, Peoples R China
2.Chinese Acad Sci, State Key Lab Transient Opt & Photon, Ctr OPT IMagery Anal & Learning OPTIMAL, Xian 710119, Shaanxi, Peoples R China
3.Nanjing Univ Sci & Technol, Coll Comp Sci & Technol, Nanjing 210094, Jiangsu, Peoples R China
4.Hong Kong Polytech Univ, Biometr Res Ctr, Hong Kong, Hong Kong, Peoples R China
推荐引用方式
GB/T 7714
Xu, Yong,Li, Xuelong,Yang, Jian,et al. Integrating Conventional and Inverse Representation for Face Recognition[J]. IEEE TRANSACTIONS ON CYBERNETICS,2014,44(10):1738-1746.
APA Xu, Yong,Li, Xuelong,Yang, Jian,Lai, Zhihui,&Zhang, David.(2014).Integrating Conventional and Inverse Representation for Face Recognition.IEEE TRANSACTIONS ON CYBERNETICS,44(10),1738-1746.
MLA Xu, Yong,et al."Integrating Conventional and Inverse Representation for Face Recognition".IEEE TRANSACTIONS ON CYBERNETICS 44.10(2014):1738-1746.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Integrating Conventi(10125KB)期刊论文出版稿限制开放CC BY请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Xu, Yong]的文章
[Li, Xuelong]的文章
[Yang, Jian]的文章
百度学术
百度学术中相似的文章
[Xu, Yong]的文章
[Li, Xuelong]的文章
[Yang, Jian]的文章
必应学术
必应学术中相似的文章
[Xu, Yong]的文章
[Li, Xuelong]的文章
[Yang, Jian]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。