Cross-Modality Face Recognition via Heterogeneous Joint Bayesian

doi:10.1109/LSP.2016.2637400

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 生物识别与安全技术

	Cross-Modality Face Recognition via Heterogeneous Joint Bayesian
	Shi, Hailin1 ; Wang, Xiaobo1 ; Yi, Dong 2; Lei, Zhen3 ; Zhu, Xiangyu1 ; Li, Stan Z.1
发表期刊	IEEE SIGNAL PROCESSING LETTERS
	2017
卷号	24 期号:1 页码:81-85
文章类型	Article
摘要	In many face recognition applications, the modalities of face images between the gallery and probe sets are different, which is known as heterogeneous face recognition. How to reduce the feature gap between images from different modalities is a critical issue to develop a highly accurate face recognition algorithm. Recently, joint Bayesian (JB) has demonstrated superior performance on general face recognition compared to traditional discriminant analysis methods like subspace learning. However, the original JB treats the two input samples equally and does not take into account the modality difference between them and may be suboptimal to address the heterogeneous face recognition problem. In this work, we extend the original JB by modeling the gallery and probe images using two different Gaussian distributions to propose a heterogeneous joint Bayesian (HJB) formulation for cross-modality face recognition. The proposed HJB explicitly models the modality difference of image pairs and, therefore, is able to better discriminate the same/different face pairs accurately. Extensive experiments conducted in the case of visible-near-infrared and ID photo versus spot face recognition problems show the superiority of the HJB over previous methods.
关键词	Cross Modality Heterogeneous Face Recognition Joint Bayesian (Jb)
WOS标题词	Science & Technology ; Technology
DOI	10.1109/LSP.2016.2637400
收录类别	SCI
语种	英语
项目资助者	National Key Research and Development Plan(2016YFC0801002) ; Chinese National Natural Science Foundation(61473291 ; AuthenMetric RD Funds ; 61572501 ; 61502491 ; 61572536)
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:000393813700003
引用统计	被引频次：8[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/173211/14379
专题	多模态人工智能系统全国重点实验室_生物识别与安全技术
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Alibaba Grp, Hangzhou 311121, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Shi, Hailin,Wang, Xiaobo,Yi, Dong,et al. Cross-Modality Face Recognition via Heterogeneous Joint Bayesian[J]. IEEE SIGNAL PROCESSING LETTERS,2017,24(1):81-85.
APA	Shi, Hailin,Wang, Xiaobo,Yi, Dong,Lei, Zhen,Zhu, Xiangyu,&Li, Stan Z..(2017).Cross-Modality Face Recognition via Heterogeneous Joint Bayesian.IEEE SIGNAL PROCESSING LETTERS,24(1),81-85.
MLA	Shi, Hailin,et al."Cross-Modality Face Recognition via Heterogeneous Joint Bayesian".IEEE SIGNAL PROCESSING LETTERS 24.1(2017):81-85.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
FINAL VERSION.pdf（742KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载