CASIA OpenIR  > 模式识别国家重点实验室  > 生物识别与安全技术研究
Video-based face recognition using a metric of average Euclidean distance
Li, JW; Wang, YH; Tan, TN
Source PublicationADVANCES IN BIOMETRIC PERSON AUTHENTICATION, PROCEEDINGS
2004
Volume3338Issue:0Pages:224-232
SubtypeArticle
AbstractThis paper presents a novel approach for video-based face recognition. We define a metric based on an average L-2 Euclidean distance between two videos as the classifier. This metric makes use of Earth Mover's Distance (EMD) as the underlying similarity measurement between videos. Earth Mover's Distance is a recently proposed metric for geometric pattern matching and it reflects the average ground distance between two distributions. Under the framework of EMD, each video is modeled as a video signature and Euclidean distance is selected as the ground distance of EMD. Since clustering algorithm is employed, video signature can well represent the overall data distribution of faces in video. Experimental results demonstrate the superior performance of our algorithm.
KeywordNone
WOS HeadingsScience & Technology ; Technology
Indexed BySCI ; ISTP
Language英语
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence ; Computer Science, Theory & Methods
WOS IDWOS:000226133000024
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/7970
Collection模式识别国家重点实验室_生物识别与安全技术研究
AffiliationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100080, Peoples R China
Recommended Citation
GB/T 7714
Li, JW,Wang, YH,Tan, TN. Video-based face recognition using a metric of average Euclidean distance[J]. ADVANCES IN BIOMETRIC PERSON AUTHENTICATION, PROCEEDINGS,2004,3338(0):224-232.
APA Li, JW,Wang, YH,&Tan, TN.(2004).Video-based face recognition using a metric of average Euclidean distance.ADVANCES IN BIOMETRIC PERSON AUTHENTICATION, PROCEEDINGS,3338(0),224-232.
MLA Li, JW,et al."Video-based face recognition using a metric of average Euclidean distance".ADVANCES IN BIOMETRIC PERSON AUTHENTICATION, PROCEEDINGS 3338.0(2004):224-232.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li, JW]'s Articles
[Wang, YH]'s Articles
[Tan, TN]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li, JW]'s Articles
[Wang, YH]'s Articles
[Tan, TN]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li, JW]'s Articles
[Wang, YH]'s Articles
[Tan, TN]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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