2012 Fiscal Year Final Research Report
A Study on A Recognition Algorithm of Handwritten Japanese DocumentUsing Syntax Self-Organization Model With Data Mining
| Project/Area Number |
22500170
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | Tokyo National College of Technology |
|---|
Principal Investigator |
SUZUKI Masato 東京工業高等専門学校, 情報工学科, 教授 (50290721)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
MATSUMOTO Akiyo 東北学院大学, 教養学部, 講師 (40413752)
|
|---|
| Co-Investigator(Renkei-kenkyūsha) |
KITAKOSHI Daisuke 東京工業高等専門学校, 情報工学科, 准教授 (50378238)
MATSUMOTO Akiyo 東北学院大学, 教養学部, 講師 (40413752)
|
|---|
| Project Period (FY) |
2010 – 2012
|
| Keywords | パターン認識 / 機械学習 / データマイニング / 自然言語処理 |
|---|
| Research Abstract |
It is difficult to realize high recognition accuracy in Japanese handwritten document recognition, since a writer's peculiarity appeared strongly in type and the text itself don’t agree in Japanese syntax. In this research, we propose the self-organization model of Japanese syntax using natural language processing a data mining, and the self-organization model of learning patterns of chinese character recognition. As a result, the recognition accuracy of Japanese handwritten document is improved compared with the conventional method.
|
Research Products
(44 results)
