Name
Abstract | ||
|---|---|---|
Gait is a unique and promising behavioral biometrics which allows to authenticate a person even at a distance from the camera. Since a matching pair of gait features are often drawn from different views due to differences in camera position/attitude and walking directions in the real world, it is important to cope with cross-view gait recognition. In this paper, we propose a discriminative approach to cross-view gait recognition using view-dependent projection matrices, unlike the existing discriminant approaches which utilize only a single common projection matrix for different views. We demonstrated the effectiveness of the proposed method through cross-view gait recognition experiments with two publicly available gait datasets. In addition, since the success of the discriminant analysis relies on the training sample size, we show the effect of transfer learning across two gait datasets as well as provide the rigorous sensitivity analysis of the proposed method against the number of training subjects ranging from 10 to approximately 1,000 subjects. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/BTAS.2014.6996272 | Biometrics |
Keywords | Field | DocType |
biometrics (access control),feature extraction,gait analysis,image matching,matrix algebra,behavioral biometrics,cross-view gait recognition,gait feature matching pair,projection matrix,view-dependent discriminative analysis | Computer vision,Economics,Pattern recognition,Gait,Discriminant,Transfer of learning,Ranging,Artificial intelligence,Linear discriminant analysis,Biometrics,Discriminative model,Sample size determination | Conference |
Citations | PageRank | References |
8 | 0.46 | 37 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Mansur, A. | 1 | 8 | 0.46 |
| Yasushi Makihara | 2 | 1012 | 70.67 |
| Daigo Muramatsu | 3 | 262 | 24.88 |
| Yasushi Yagi | 4 | 1752 | 186.22 |