The OU-ISIR Gait Database Comprising the Large Population Dataset and Performance Evaluation of Gait Recognition

被引:283
作者
Iwama, Haruyuki [1 ]
Okumura, Mayu [1 ]
Makihara, Yasushi [1 ]
Yagi, Yasushi [1 ]
机构
[1] Osaka Univ, Dept Intelligent Media, Inst Sci & Ind Res, Ibaraki, Osaka 5670047, Japan
关键词
Gait database; gait recognition; large population; performance evaluation; VIEW ANGLE; IMAGE; REPRESENTATION; TEMPLATE; QUALITY;
D O I
10.1109/TIFS.2012.2204253
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
This paper describes the world's largest gait database-the "OU-ISIR Gait Database, Large Population Dataset"-and its application to a statistically reliable performance evaluation of vision-based gait recognition. Whereas existing gait databases include at most 185 subjects, we construct a larger gait database that includes 4007 subjects (2135 males and 1872 females) with ages ranging from 1 to 94 years. The dataset allows us to determine statistically significant performance differences between currently proposed gait features. In addition, the dependences of gait-recognition performance on gender and age group are investigated and the results provide several novel insights, such as the gradual change in recognition performance with human growth.
引用
收藏
页码:1511 / 1521
页数:11
相关论文
共 47 条
[1]  
[Anonymous], 2006, INT SERIES BIOMETRIC
[2]  
[Anonymous], 2011, P 2011 INT JOINT C B, DOI 10.1109/IJCB.2011.6117531
[3]  
[Anonymous], P 23 IEEE C COMP VIS
[4]  
[Anonymous], 2001, CMU MOTION BODY MOBO
[5]  
Bashir K., 2009, P 3 INT C IM CRIM DE
[6]   Gait recognition without subject cooperation [J].
Bashir, Khalid ;
Xiang, Tao ;
Gong, Shaogang .
PATTERN RECOGNITION LETTERS, 2010, 31 (13) :2052-2060
[7]  
Bouchrika I., 2008, P 8 IEEE INT C AUT F, P1
[8]  
Boykov YY, 2001, EIGHTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOL I, PROCEEDINGS, P105, DOI 10.1109/ICCV.2001.937505
[9]  
Chalidabhongse T, 2001, UMD DATABASE HUMAN I
[10]  
Grother P.J., 2004, FACE RECOGNITION VEN