Sign Language Recognition System based on the Generation and Recognition Model for Human Arm Movement
| Project/Area Number |
25330335
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Life / Health / Medical informatics
|
|---|
| Research Institution | Toyohashi University of Technology |
|---|
Principal Investigator |
Fukumura Naohiro 豊橋技術科学大学, 工学(系)研究科(研究院), 准教授 (90293753)
|
|---|
| Research Collaborator |
IGARI Shinpei 豊橋技術科学大学, 大学院工学研究科
SHISHIDO Emiko 名古屋大学, 医学系研究科, 特別研究員 (40723101)
|
|---|
| Project Period (FY) |
2013-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
Fiscal Year 2015: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2014: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2013: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
|
|---|
| Keywords | 手話単語認識 / 躍度最小軌道 / ヒト腕の運動 / ジェスチャー / 手話 / ジェスチャー認識 / ジャーク最小軌道 / 経由点 / DPマッチング / Multi-Stream HMM / 手話翻訳 / アイ・ハンド・コーディネーション |
|---|
| Outline of Final Research Achievements |
A hypothesis that human skillful hand motions are generated as optimal trajectories that represent and store only constraint conditions such as a few via-points where the hand pass in addition to the start and the end point of the trajectory in the brain. We examined this hypothesis by simulating the curved hand movements and the orchestra's conducting motion trajectory and gaze measurement experiment when drawing the curve. We also proposed algorithms for sign language recognition using information about these via-points. We measured 360 sign language words and showed recognition rate of 90.2% in the case of sign language words expressed only by both arm movement and 90.0% in case of sign language words expressed only with a dominant hand, respectively.
|
Report
(5 results)
Research Products
(18 results)
