| Project/Area Number |
12680381
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Toyohashi University of Technology |
|---|
Principal Investigator |
YAMAMOTO Shinji Toyohashi University of Technology, Faculty of Engineering, Professor, 工学部, 教授 (80230556)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
EZAKI Nobuo Toba National College of Technology, Information and Control Engineering Department, Research Associate, 制御情報工学科, 助手 (30311038)
KIYOTA Kimiyasu Kumamoto National College of Technology, Department of Electronic Engineering, Associate Professor, 電子工学科, 助教授 (80186353)
|
|---|
| Project Period (FY) |
2000 – 2001
|
| Project Status |
Completed (Fiscal Year 2001)
|
| Budget Amount *help |
¥3,100,000 (Direct Cost: ¥3,100,000)
Fiscal Year 2001: ¥1,300,000 (Direct Cost: ¥1,300,000)
Fiscal Year 2000: ¥1,800,000 (Direct Cost: ¥1,800,000)
|
|---|
| Keywords | On-line character recognition / Disabled persons / Error correction / 日本語入力 |
|---|
| Research Abstract |
We have developed a pen-based Japanese character input system for the visually disabled persons, especially persons with acquired blinds. This system is composed of a character input tablet, a voice synthesizer and character recognition system. The main purpose of this system is to be applied to an electronic mail system for the blind persons. The results we got in this grant term are as follows:
(1) Data base construction of the handwritten characters 3216 categories of Japanese characters, totally about 100 thousand characters were gathered from visually disabled persons and blindfold persons.
(2) Enhancement of on-line character recognition algorithm Before we started this project, we had already developed an recognition algorithm for about 1000 category Japanese characters (Kyoiku Kanji Category). We enhanced this algorithm to apply 3216 category Japanese characters, including JIS No. 1 level Chinese characters, Hiragana, Katakana, Symbol, Alphabet.
(3) Selection of the error correction algorithms of characters by word level knowledge. Three kinds of error correction algorithm were comparatively applied and evaluated. As the result, the Trigram method was found to be a best choice for our purpose.
(4) Prototype of man-machine interface device We developed a prototype of man-machine interface device. This device is composed of an electric tablet for writing a character by the right hand, a hand controller for controlling the system condition by the left hand.
(5) Document control system for visually disabled persons Document control system in CPU, like file management, document editing, and e-mail receiving/transmitting, was developed.
|
