Generation of diversiform characters using a computational handwriting model
| Project/Area Number |
11680384
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Nagaoka University of Technology |
|---|
Principal Investigator |
WADA Yasuhiro Nagaoka University of technology, Faculty of Engineering, Associate Professor, 工学部, 助教授 (70293248)
|
|---|
| Project Period (FY) |
1999 – 2001
|
| Project Status |
Completed (Fiscal Year 2001)
|
| Budget Amount *help |
¥3,800,000 (Direct Cost: ¥3,800,000)
Fiscal Year 2001: ¥500,000 (Direct Cost: ¥500,000)
Fiscal Year 2000: ¥500,000 (Direct Cost: ¥500,000)
Fiscal Year 1999: ¥2,800,000 (Direct Cost: ¥2,800,000)
|
|---|
| Keywords | Handwriting model / Genetic Algorithm / Pattern recognition / Handwritten character / Database / Recognition rate / 書字運動 / 経由点 / 文字変形 |
|---|
| Research Abstract |
In pattern recognition, a large number of diversiform characters is necessary to train / test a handwritten character recognition system: However, it is not easy to collect a large number of natural samples. The artificial diversification of characters has been suggested as one means of collecting a variety of characters. In this research, we show that a handwriting model can be applied to the diversification of characters. The characters diversified by the model can be used as a database of character images for training / testing purposes. Wada ＆ Kawato's handwriting model is based on an optimal principle and the feature space of the characters includes sets of viapoints extracted from actual handwritten characters. The handwriting model can be used to generate diversiform characters by changing viapoint information.
In this research, we propose a method for generating a diversification of characters by changing viapoint information based on a genetic algorithm and we show that the accuracy of a handwritten character recognition system that uses the character generated by the proposed method as the training data, is equivalent to that of a system composed by using natural dat.
|
Report
(4 results)
Research Products
(14 results)
