Toward ultimate pattern recognition by massive instances
| Project/Area Number |
23650089
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | Kyushu University |
|---|
Principal Investigator |
UCHIDA Seiichi 九州大学, システム情報科学研究院, 教授 (70315125)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
KANEKO Kunihiko 九州大学, 大学院・システム情報科学研究院, 准教授50274494 (50274494)
YAOKAI Feng 九州大学, 大学院・システム情報科学研究院, 助教 (60363389)
|
|---|
| Project Period (FY) |
2011 – 2012
|
| Project Status |
Completed (Fiscal Year 2012)
|
| Budget Amount *help |
¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2012: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2011: ¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
|
|---|
| Keywords | パターン認識 / ネットワーク解析 / パターン分布解析 / パターン分布 / フォント / 文字認識 / ビッグデータ |
|---|
| Research Abstract |
he ambitious goal of this research is to understand the real distribution of character patterns. Ideally, if we can collect all possible character patterns, we can totally understand how they are distributed in the image space. In addition, we also have the perfect character recognizer because we know the correct class for any character image. Of course, it is practically impossible to collect all those patterns - however, if we collect character patterns massively and analyze how the distribution changes according to the increase of patterns, we will be able to estimate the real distribution asymptotically. For this purpose, we use 822,714 manually ground-truthed handwritten digit patterns. The distribution of those patterns are observed by nearest neighbor analysis and network analysis, both of which do not make any approximation (such as low-dimensional representation) and thus do not corrupt the details of the distribution.
|
Report
(3 results)
Research Products
(25 results)
