Development of Mobile Sign Language Recognition System using First Person View Fish-eye Camera
| Project/Area Number |
25730138
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Kyushu Institute of Technology |
|---|
Principal Investigator |
Kawano Hideaki 九州工業大学, 大学院工学研究院, 准教授 (00404096)
|
|---|
| Project Period (FY) |
2013-04-01 – 2016-03-31
|
| Project Status |
Completed (Fiscal Year 2015)
|
| Budget Amount *help |
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2015: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2014: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2013: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | 手話認識 / 一人称視点 / SIFT / HMM / 画像特徴量 / 隠れマルコフモデル / 画像追跡 |
|---|
| Outline of Final Research Achievements |
Indeed a lot of studies have been reported on the sign language recognition system, but there are few studies suitable for daily use. In this study, we proposed a sign language recognition system available as daily use. The system is wearable but no restraints in gesturing because sign languages are sensed by a camera mounted on the user’s chest. In discriminating the form of hand, a state-of-art feature descriptor, i.e. SIFT, is employed. It is considered that the SIFT is suitable for wearable systems because of the low computational costs. The effectiveness of the proposed method is verified by an experiment using 22 sign language words. As a result, we obtained good results for 19 words among the 22 words.
|
Report
(4 results)
Research Products
(9 results)
