Video-based face recognition using a metric of average Euclidean distance
Li, JW; Wang, YH; Tan, TN
2004
发表期刊ADVANCES IN BIOMETRIC PERSON AUTHENTICATION, PROCEEDINGS
卷号3338期号:0页码:224-232
文章类型Article
摘要This 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.
关键词None
WOS标题词Science & Technology ; Technology
收录类别SCI ; ISTP
语种英语
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods
WOS记录号WOS:000226133000024
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/7970
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Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100080, Peoples R China
推荐引用方式
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.
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
[Li, JW]的文章
[Wang, YH]的文章
[Tan, TN]的文章
百度学术
百度学术中相似的文章
[Li, JW]的文章
[Wang, YH]的文章
[Tan, TN]的文章
必应学术
必应学术中相似的文章
[Li, JW]的文章
[Wang, YH]的文章
[Tan, TN]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。