Presentation | 2017-10-20 Effective skeletons for sign language recognition Tomoya Kodama, Takeshi Saitoh, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | With the reasonable motion sensor Microsoft Kinect was marketed, a lot of sign language recognition methods using Kinect have been proposed. However, in the conventional researches, in skeleton information that can be obtained from Kinect, there are no discussion for efficient skeleton information for sign language recognition task. In this research, although we use the position feature and movement feature which are proposed in the previous research, we investigate the effective skeleton information for sign language recognition by changing the skeleton information to consider, such as hands, wrists, elbows, shoulder. As the recognition results using public dataset ChaLearn, it was found that high recognition accuracy can be obtained by using the position and movement feature of both hands and elbows. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Sign language recognition / skeleton information / ChaLearn dataset |
Paper # | SP2017-49,WIT2017-45 |
Date of Issue | 2017-10-12 (SP, WIT) |
Conference Information | |
Committee | WIT / SP |
---|---|
Conference Date | 2017/10/19(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Tobata Library of Kyutech (Kitakyushu) |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Chikamune Wada(Kyushu Inst. of Tech.) / Yoichi Yamashita(Ritsumeikan Univ.) |
Vice Chair | Daisuke Wakatsuki(Tsukuba Univ. of Tech.) / Hiroki Mori(Utsunomiya Univ.) |
Secretary | Daisuke Wakatsuki(Nagoya Inst. of Tech.) / Hiroki Mori(AIST) |
Assistant | Takeaki Shionome(*) / Manabi Miyagi(Tsukuba Univ. of Tech.) / Takashi Handa(Saitama Industrial Technology Center) / Kei Hashimoto(Nagoya Inst. of Tech.) / Satoshi Kobashikawa(NTT) |
Paper Information | |
Registration To | Technical Committee on Well-being Information Technology / Technical Committee on Speech |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Effective skeletons for sign language recognition |
Sub Title (in English) | |
Keyword(1) | Sign language recognition |
Keyword(2) | skeleton information |
Keyword(3) | ChaLearn dataset |
1st Author's Name | Tomoya Kodama |
1st Author's Affiliation | Kyushu Institute of Technology(Kyutech) |
2nd Author's Name | Takeshi Saitoh |
2nd Author's Affiliation | Kyushu Institute of Technology(Kyutech) |
Date | 2017-10-20 |
Paper # | SP2017-49,WIT2017-45 |
Volume (vol) | vol.117 |
Number (no) | SP-250,WIT-251 |
Page | pp.pp.83-87(SP), pp.83-87(WIT), |
#Pages | 5 |
Date of Issue | 2017-10-12 (SP, WIT) |