Abstract | ||
---|---|---|
In the gait recognition, the dependency to the direction of walking is very serious problem. To reduce this dependency, we propose a view synthesis method based on the planar homography. However, even though the synthesized gait is used, shape information is not enough to recognize individual. Thus, in this paper, we use shape sequence descriptor for recognition, which describes shape information and variation according to motion at a same time. Our experiments show that the proposed method efficiently reduces the dependency to directional variations of gait. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1007/978-3-642-27180-9_59 | GRID AND DISTRIBUTED COMPUTING |
Keywords | Field | DocType |
Gait Recognition, Biometrics, Canonical View, Shape Sequence, View Synthesis | Computer vision,Gait,Pattern recognition,Computer science,View synthesis,Artificial intelligence,Biometrics,Planar homography | Conference |
Volume | ISSN | Citations |
261 | 1865-0929 | 0 |
PageRank | References | Authors |
0.34 | 3 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Seungdo Jeong | 1 | 25 | 8.82 |
Young-Suk Lee | 2 | 264 | 25.78 |
Keun-Wang Lee | 3 | 24 | 13.44 |
Jungwon Cho | 4 | 46 | 11.21 |