| Project/Area Number |
17500387
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Rehabilitation science/Welfare engineering
|
|---|
| Research Institution | Kumamoto National College of Technology |
|---|
Principal Investigator |
KIYOTA Kimiyasu Kumamoto National College of Technology, Department of Information and Communication, Professor, 情報通信工学科, 教授 (80186353)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
SHIMAKAWA Manabu Kumamoto National College of Technology, Department of Information and Computer Science, Associate Professor, 情報工学科, 助教授 (40259958)
EZAKI Nobuo Toba National College of Maritime Technology, Department of Control and Information, Lecturer, 制御情報工学科, 講師 (30311038)
|
|---|
| Project Period (FY) |
2005 – 2006
|
| Project Status |
Completed (Fiscal Year 2006)
|
| Budget Amount *help |
¥3,400,000 (Direct Cost: ¥3,400,000)
Fiscal Year 2006: ¥1,400,000 (Direct Cost: ¥1,400,000)
Fiscal Year 2005: ¥2,000,000 (Direct Cost: ¥2,000,000)
|
|---|
| Keywords | Blind user / Ubiquitous / Ultra mobile PCs / Handicap support / Pen-based interface / 携帯端末(PDA) / ペン入力PC |
|---|
| Research Abstract |
We propose a pen-based note-taking system, which is named the 'Pen-Talker' on the ultra mobile PCs for blind person. A blind novice user with acquired blindness is able to input Japanese characters directly instead of a keyboard without well training by using the 'Pen-Talker'. We have studied the system design concept of the 'Pen-Talker'. We also investigate a higher recognition engine based on the hybrid recognition, which is integration of on-line and off-line recognition algorithm, and we restructure the input interface by the ultra mobile PCs with a voice assistance function. Screen information is given to user via built-in a screen reader. Therefore the system can be used as a note pad software using a simple button operation for even blind novice user. As a result of the recognition experiment, recognition accuracy has improved to 93.3% for eight blind subjects. This is an extremely high score compared with the previous our system. Consequently, we confirmed the practical use possibility of the proposed system.
|
