| Presentation | 2016-03-05 Real-time Sign Language Recognition by Kinect v2 based on three Elements of Sign Language Mika Hatano, Shinji Sako, Tadashi Kitamura, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Existing research of sign language recognition deals with only small vocabulary. Sign language has no basic database and unit of recognition yet, compared with spoken language. However, adopting knowledge of linguistics can be useful to model sign language words for efficient large vocabulary recognition. We developed a real-time Japanese sign language recognition system. The system based on an electronic sign language word dictionary which defines each words with three elements of sign language: motion, position, and shape. Our system employs Kinect v2 sensor to obtain features from sign language motion. We apply a contour-based method to hand shape recognition which is the most difficult process to speed up in three elements. Also, our system does not use large amount of learning data. We conduct experiments to recognize Japanese sign language words targeted sign language interpreters. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | sign language recognition / real-time / Kinect / contour-based recognition |
| Paper # | WIT2015-99 |
| Date of Issue | 2016-02-26 (WIT) |
| Conference Information | |
| Committee | WIT |
|---|---|
| Conference Date | 2016/3/4(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Tusukuba Univ. of Tech.(Tsukuba) |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Hearing / Visually impaired person support technology, etc. |
| Chair | Kiyohiko Nunokawa(Tokyo International Univ.) |
| Vice Chair | Chikamune Wada(Kyushu Inst. of Tech.) |
| Secretary | Chikamune Wada(Nagoya Inst. of Tech.) |
| Assistant | Tomohiro Amemiya(NTT) / Takeaki Shionome(Tsukuba Univ. of Tech.) / Manabi Miyagi(Tsukuba Univ. of Tech.) |
| Paper Information | |
| Registration To | Technical Committee on Well-being Information Technology |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Real-time Sign Language Recognition by Kinect v2 based on three Elements of Sign Language |
| Sub Title (in English) | |
| Keyword(1) | sign language recognition |
| Keyword(2) | real-time |
| Keyword(3) | Kinect |
| Keyword(4) | contour-based recognition |
| Keyword(5) | |
| 1st Author's Name | Mika Hatano |
| 1st Author's Affiliation | Nagoya Institute of Technology(NITech) |
| 2nd Author's Name | Shinji Sako |
| 2nd Author's Affiliation | Nagoya Institute of Technology(NITech) |
| 3rd Author's Name | Tadashi Kitamura |
| 3rd Author's Affiliation | Nagoya Institute of Technology(NITech) |
| Date | 2016-03-05 |
| Paper # | WIT2015-99 |
| Volume (vol) | vol.115 |
| Number (no) | WIT-491 |
| Page | pp.pp.59-64(WIT), |
| #Pages | 6 |
| Date of Issue | 2016-02-26 (WIT) |