| Presentation | 2011-03-11 Person identification robust to changes in appearance Yumi IWASHITA, Koji UCHINO, Ryo KURAZUME, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper presents a novel method for gait-based person identification robust to changes in appearance. Gait is sensitive to appearance changes, such as variations of clothes and carrying conditions, so the correct classification rate is reduced in case target's appearance condition is different from that in the database. To deal with this problem, a part-based gait identification method has been proposed. In this method the human body is divided into eight parts, and the discrimination capability of each part, which is trained with training datasets including various types of clothes, is controlled to correspond to different changes of clothes. However, the correct classification rate would be reduced in case target's clothes are not included in the training datasets. So we propose a new part-based person identification method, where the discrimination capability at each part is directly controlled based on gait features between gallery datasets and probe dataset. Experiments using a gait database CASIA show the effectiveness of the proposed method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Gait / person identification / affine moment invariants / local features |
| Paper # | PRMU2010-281 |
| Date of Issue |
| Conference Information | |
| Committee | PRMU |
|---|---|
| Conference Date | 2011/3/3(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Pattern Recognition and Media Understanding (PRMU) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Person identification robust to changes in appearance |
| Sub Title (in English) | |
| Keyword(1) | Gait |
| Keyword(2) | person identification |
| Keyword(3) | affine moment invariants |
| Keyword(4) | local features |
| 1st Author's Name | Yumi IWASHITA |
| 1st Author's Affiliation | Information Science and Electrical Engineering, Kyushu University() |
| 2nd Author's Name | Koji UCHINO |
| 2nd Author's Affiliation | Electrical Engineering and Computer Science, Kyushu University |
| 3rd Author's Name | Ryo KURAZUME |
| 3rd Author's Affiliation | Information Science and Electrical Engineering, Kyushu University |
| Date | 2011-03-11 |
| Paper # | PRMU2010-281 |
| Volume (vol) | vol.110 |
| Number (no) | 467 |
| Page | pp.pp.- |
| #Pages | 5 |
| Date of Issue | |