Character recognition by image analysis in the digitization of contents written in traditional Mongolian script
Project/Area Number |
24700242
|
Research Category |
Grant-in-Aid for Young Scientists (B)
|
Allocation Type | Multi-year Fund |
Research Field |
Library and information science/Humanistic social informatics
|
Research Institution | Shizuoka University |
Principal Investigator |
|
Project Period (FY) |
2012-04-01 – 2015-03-31
|
Project Status |
Completed (Fiscal Year 2014)
|
Budget Amount *help |
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2014: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2013: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2012: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
Keywords | 伝統モンゴル文字 / 文字認識 / 文書の画像解析 / デジタル化 / 資料のデジタル化 |
Outline of Final Research Achievements |
The classical/traditional Mongolian script was in common use in Mongolia up to 1946. There are many traditional Mongolian documents reserved in image form. This study aimed to develop character recognition techniques for Mongolian script. Results will be used in the digitization process of contents written in traditional script and in the online retrieval. Several results obtained so far: (1) Implementation of layout analysis of document images by considering that Mongolian character is a left-to-right vertical writing and that has no-space between characters, (2) Development of an efficient word search method for Mongolian script, (3) Modeling of deformation rule of Mongolian characters, and (4) Classification of character elements by using Adaboost, further to achieve automatic recognition for Mongolian script. We will improve the recognition accuracy by implementing a statistical model for word, character and elements of traditional Mongolian, in the future.
|
Report
(4 results)
Research Products
(11 results)