Learning Discriminant Face Descriptor
Lei, Zhen1,2; Pietikainen, Matti3; Li, Stan Z.1,2
2014-02-01
发表期刊IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷号36期号:2页码:289-302
文章类型Article
摘要Local feature descriptor is an important module for face recognition and those like Gabor and local binary patterns (LBP) have proven effective face descriptors. Traditionally, the form of such local descriptors is predefined in a handcrafted way. In this paper, we propose a method to learn a discriminant face descriptor (DFD) in a data-driven way. The idea is to learn the most discriminant local features that minimize the difference of the features between images of the same person and maximize that between images from different people. In particular, we propose to enhance the discriminative ability of face representation in three aspects. First, the discriminant image filters are learned. Second, the optimal neighborhood sampling strategy is soft determined. Third, the dominant patterns are statistically constructed. Discriminative learning is incorporated to extract effective and robust features. We further apply the proposed method to the heterogeneous (cross-modality) face recognition problem and learn DFD in a coupled way (coupled DFD or C-DFD) to reduce the gap between features of heterogeneous face images to improve the performance of this challenging problem. Extensive experiments on FERET, CAS-PEAL-R1, LFW, and HFB face databases validate the effectiveness of the proposed DFD learning on both homogeneous and heterogeneous face recognition problems. The DFD improves POEM and LQP by about 4.5 percent on LFW database and the C-DFD enhances the heterogeneous face recognition performance of LBP by over 25 percent.
关键词Face Recognition Discriminant Face Descriptor Image Filter Learning Discriminant Learning Heterogeneous Face Recognition
WOS标题词Science & Technology ; Technology
关键词[WOS]LOCAL BINARY PATTERNS ; IMAGE CLASSIFICATION ; RECOGNITION ; REPRESENTATION ; SCALE ; HISTOGRAM ; FEATURES ; MODEL
收录类别SCI
语种英语
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号WOS:000328899500007
引用统计
被引频次:143[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/8024
专题模式识别国家重点实验室_生物识别与安全技术研究
作者单位1.Chinese Acad Sci, Ctr Biometr & Secur Res, Beijing 100190, Peoples R China
2.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China
3.Univ Oulu, Ctr Machine Vis Res, FI-90014 Oulu, Finland
推荐引用方式
GB/T 7714
Lei, Zhen,Pietikainen, Matti,Li, Stan Z.. Learning Discriminant Face Descriptor[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2014,36(2):289-302.
APA Lei, Zhen,Pietikainen, Matti,&Li, Stan Z..(2014).Learning Discriminant Face Descriptor.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,36(2),289-302.
MLA Lei, Zhen,et al."Learning Discriminant Face Descriptor".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 36.2(2014):289-302.
条目包含的文件
条目无相关文件。
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
[Lei, Zhen]的文章
[Pietikainen, Matti]的文章
[Li, Stan Z.]的文章
百度学术
百度学术中相似的文章
[Lei, Zhen]的文章
[Pietikainen, Matti]的文章
[Li, Stan Z.]的文章
必应学术
必应学术中相似的文章
[Lei, Zhen]的文章
[Pietikainen, Matti]的文章
[Li, Stan Z.]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。