| Presentation | 2008-06-19 Sign Language Recognition Based on Position and Movement Using Hidden Markov Model Masaru MAEBATAKE, Masafumi NISHIDA, Yasuo HORIUCHI, Shingo KUROIWA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In sign language, the meaning of a word varies with hand positions. Thus, we studied on word recognition method integrated the position and movement of hands. The hand position was normalized for each utterance. We extracted the difference between frames as the movement from the position coordinate. The word recognition was performed using hidden Markov model based on these features. Furthermore, we assumed that the importance of the position and movement of hands changes with words and also performed the word recognition by the multi-stream HMM. As a result, recognition accuracy was 67.1% by using only hand position and was 79.9% by using both of the position and movement of hands. Moreover, we demonstrated that the importance of the movement was larger than the position by the multi-stream HMM. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Sign Language / hand position / hand movement / hidden Markov model / mufti-stream |
| Paper # | DE2008-2,PRMU2008-20 |
| Date of Issue |
| Conference Information | |
| Committee | DE |
|---|---|
| Conference Date | 2008/6/12(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 | Data Engineering (DE) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Sign Language Recognition Based on Position and Movement Using Hidden Markov Model |
| Sub Title (in English) | |
| Keyword(1) | Sign Language |
| Keyword(2) | hand position |
| Keyword(3) | hand movement |
| Keyword(4) | hidden Markov model |
| Keyword(5) | mufti-stream |
| 1st Author's Name | Masaru MAEBATAKE |
| 1st Author's Affiliation | Graduate School of Advanced Intergration Science, Chiba University() |
| 2nd Author's Name | Masafumi NISHIDA |
| 2nd Author's Affiliation | Graduate School of Advanced Intergration Science, Chiba University |
| 3rd Author's Name | Yasuo HORIUCHI |
| 3rd Author's Affiliation | Graduate School of Advanced Intergration Science, Chiba University |
| 4th Author's Name | Shingo KUROIWA |
| 4th Author's Affiliation | Graduate School of Advanced Intergration Science, Chiba University |
| Date | 2008-06-19 |
| Paper # | DE2008-2,PRMU2008-20 |
| Volume (vol) | vol.108 |
| Number (no) | 93 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |