Presentation | 2003/3/15 A Detection Method of Sign Word Sequences Based on the Angular Jerk of Human Arm Movements Michinori AKITA, Naohiro FUKUMURA, Yoji UNO, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Proper segmentation of sign-language into words improves recognition efficiency in the recognition system. However, it is a challenge for the segmentation, because the sign-language sequences include some preparatory actions. Therefore, we tested a word detection method by the angular jerk of human arm movements, considering the relation between unsmooth parts and word boundaries. The parts in which there is a large amount of joint angular jerk were detected as word boundaries. To verify the validity of the proposed method, the psychophysical experiments were executed by two subjects who were well known to sign-language. The results indicate that the feature of sign-word movements can be detected by this method. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | sign-language recognition system / criterion of human arm movement / joint angular jerk |
Paper # | WIT2002-78 |
Date of Issue |
Conference Information | |
Committee | WIT |
---|---|
Conference Date | 2003/3/15(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 | Well-being Information Technology(WIT) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | A Detection Method of Sign Word Sequences Based on the Angular Jerk of Human Arm Movements |
Sub Title (in English) | |
Keyword(1) | sign-language recognition system |
Keyword(2) | criterion of human arm movement |
Keyword(3) | joint angular jerk |
1st Author's Name | Michinori AKITA |
1st Author's Affiliation | Department of Information and Computer Sciences, Toyohashi University of Technology() |
2nd Author's Name | Naohiro FUKUMURA |
2nd Author's Affiliation | Department of Information and Computer Sciences, Toyohashi University of Technology |
3rd Author's Name | Yoji UNO |
3rd Author's Affiliation | Department of Information and Computer Sciences, Toyohashi University of Technology |
Date | 2003/3/15 |
Paper # | WIT2002-78 |
Volume (vol) | vol.102 |
Number (no) | 739 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |