Preparing a test bed for digital archives of historical documents in Asia

• Project/Area Number: 24300095
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Partial Multi-year Fund
• Section: 一般
• Research Field: Library and information science/Humanistic social informatics
• Research Institution: Tokyo University of Agriculture and Technology
• Principal Investigator: NAKAGAWA Masaki 東京農工大学, 工学(系)研究科(研究院), 教授 (10126295)
• Co-Investigator(Kenkyū-buntansha): ZHU Belin 東京農工大学, 大学院工学研究院, 助教 (50466918) ; SAITO Takafumi 東京農工大学, 大学院工学研究院, 教授 (60293007) ; HOTTA seiji 東京農工大学, 大学院工学研究院, 准教授 (90346932)
• Project Period (FY): 2012-04-01 – 2016-03-31
• Project Status: Completed (Fiscal Year 2015)
• Budget Amount: ¥16,770,000 (Direct Cost: ¥12,900,000、Indirect Cost: ¥3,870,000); Fiscal Year 2015: ¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000); Fiscal Year 2014: ¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000); Fiscal Year 2013: ¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000); Fiscal Year 2012: ¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
• Keywords: 古文書 / アーカイブ / 画面処理 / 言語処理 / 文字認識 / 画像処理

Outline of Final Research Achievements

This research studied a test bed for digital archives of historical documents in Asia. For Vietnamese Chunom documents, we made OCR of more than 40,000 character categories. For wooden tablets excavated from the Heijo palace site, we made an annotation tool including noise reduction and extraction. This annotation tool is availed for archiving an enormous amount of broken pieces of wooden tablets. We are extending the research to other languages in Asia.

Research Products

• [Int'l Joint Research] ホーチミン市科学大学(ベトナム)
• [Journal Article] Combination of Global and Local Contexts for Text/Non-text Classification in Heterogeneous Online Handwritten Documents (2016)
  • Author(s): Truyen Van Phan and Masaki Nakagawa
  • Journal Title: Pattern Recognition Volume: Vol. 51 Pages: 112-124
  • DOI: 10.1016/j.patcog.2015.07.012
  • Peer Reviewed / Open Access / Int'l Joint Research / Acknowledgement Compliant
• [Journal Article] A Nom historical document recognition system for digital archiving (2015)
  • Author(s): Truyen Van Phan, Kha Cong Nguyen, and Masaki Nakagawa
  • Journal Title: International Journal on Document Analysis and Recognition (IJDAR) Volume: Vol. 18 Issue: 1 Pages: 1-16
  • DOI: 10.1007/s10032-015-0257-8
  • Peer Reviewed / Open Access / Int'l Joint Research / Acknowledgement Compliant
• [Journal Article] 木簡画像集録システムの設計と実現 (2013)
  • Author(s): Phan Van Truyen，中川正樹，馬場基，渡邊晃宏
  • Journal Title: 日本情報考古学会 Volume: Vol.19, No.1･2, Pages: 1-12
  • NAID: 40019988179
  • Peer Reviewed
• [Presentation] Text-Line and Character Segmentation for Offline Recognition of Handwritten Japanese Tex (2016)
  • Author(s): Kha Cong Nguyen, Nakagawa Masaki
  • Organizer: IEICE technical report
  • Place of Presentation: 産業技術総合研究所 臨海副都心センター 東京都江東区
  • Year and Date: 2016-03-24
• [Presentation] Preparation of an Unconstrained Vietnamese Online Handwriting Database and Recognition Experiments by BLSTM (2016)
  • Author(s): Hung Tuan Nguyen，Cuong Tuan Nguyen，Pham The Bao，Masaki Nakagawa
  • Organizer: IEICE technical report
  • Place of Presentation: 産業技術総合研究所 臨海副都心センター 東京都江東区
  • Year and Date: 2016-03-24
• [Presentation] オンライン手書き文書に対するBLSTMニューラルネットワークによる文字・図形分離の再検討 (2016)
  • Author(s): 稲谷壮一郎，中川正樹
  • Organizer: 信学技報
  • Place of Presentation: 産業技術総合研究所 臨海副都心センター 東京都江東区
  • Year and Date: 2016-03-24
• [Presentation] An Improved Segmentation of Online English Handwritten Text using Recurrent Neural Networks (2015)
  • Author(s): Cuong Tuan Nguyen and Masaki Nakagawa
  • Organizer: in Proceeding of the 3rd IAPR Asian Conference on Pattern Recognition (ACPR)
  • Place of Presentation: MALAYSIA KUALA LUMPUR
  • Year and Date: 2015-11-03
  • Int'l Joint Research
• [Presentation] A System to Annotate and Cluster Pieces of Mokkan (2015)
  • Author(s): Kha Cong NGUYEN, Truyen Van PHAN, Masaki NAKAGAWA
  • Organizer: in Proceeding of the 2015 Fourth ICT International Student Project Conference
  • Place of Presentation: Tokyo University of Agriculture and Technology, Tokyo, Japan 東京都小金井市
  • Year and Date: 2015-05-23
  • Int'l Joint Research
• [Presentation] A Vietnamese Online Handwriting Database (2015)
  • Author(s): Hung Tuan NGUYEN, Cuong Tuan NGUYEN, Pham The BAO, Masaki NAKAGAWA
  • Organizer: in Proceeding of the 2015 Fourth ICT International Student Project Conference
  • Place of Presentation: Tokyo University of Agriculture and Technology, Tokyo, Japan 東京都小金井市
  • Year and Date: 2015-05-23
  • Int'l Joint Research
• [Presentation] 失われた言語チュノムによる古文書の完全電子化に向けて (2014)
  • Author(s): 中川正樹，Phan Van Truyen
  • Organizer: 日本情報考古学会
  • Place of Presentation: 東京農工大学（東京都小金井市）
  • Year and Date: 2014-09-27 – 2014-09-28
• [Presentation] Text/Non-Text Classification in Online Handwritten Documents with Recurrent Neural Networks (2014)
  • Author(s): Truyen Van Phan, and Masaki Nakagawa
  • Organizer: he 14th International Conference on Frontiers in Handwriting Recognition (ICFHR2014)
  • Place of Presentation: Crete, Greece
  • Year and Date: 2014-09-01 – 2014-09-04
• [Presentation] A semi-incremental recognition method for online handwritten English text (2014)
  • Author(s): Cuong Tuan Nguyen, Bilan Zhu and Masaki Nakagawa
  • Organizer: the 14th International Conference on Frontiers in Handwriting Recognition (ICFHR2014)
  • Place of Presentation: Crete, Greece
  • Year and Date: 2014-09-01 – 2014-09-04
• [Presentation] Construction of a Text Digitization System for Nôm Historical Documents (2014)
  • Author(s): Truyen Van Phan, and Masaki Nakagawa
  • Organizer: the International Conference on Digital Access to Textual Cultural Heritage (DATeCH2014)
  • Place of Presentation: Madrid, Spain
  • Year and Date: 2014-05-19 – 2014-05-20
• [Presentation] A System for Recognizing Online Handwritten Mathematical Expressions and Improvement of Structure Analysis (2014)
  • Author(s): Anh Duc LE, Truyen Van PHAN, and Masaki NAKAGAWA
  • Organizer: the 11th IAPR International Workshop on Document Analysis Systems (DAS 2014)
  • Place of Presentation: Tours, France
  • Year and Date: 2014-04-07 – 2014-04-10
• [Presentation] MokkAnnotator – A System for Archiving Mokkan Images
  • Author(s): Truyen Van PHAN, Hajime BABA, Akihiro WATANABE and Masaki NAKAGAWA
  • Organizer: Proc. 16th International Graphonomics Society Conference (IGS2013),
  • Place of Presentation: 奈良,日本
• [Presentation] A Re-Assembling Scheme of Fragmented Mokkan Images
  • Author(s): Truyen Van Phan, Hajime Baba, Akihiro Watanabe, and Masaki Nakagawa
  • Organizer: Proc. 2nd International Workshop on Historical Document Imaging and Processing (HIP'13),
  • Place of Presentation: Washington DC, USA
• [Presentation] semi-incremental recognition method for on-line handwritten Japanese text
  • Author(s): Cuong Tuan Nguyen, Bilan Zhu and Masaki Nakagawa
  • Organizer: Proc. 12th International Conference on Document Analysis and Recognition (ICDAR2013)
  • Place of Presentation: Washington DC, USA
• [Funded Workshop] in Proceeding of the 3rd IAPR Asian Conference on Pattern Recognition (ACPR) (2015)
  • Place of Presentation: Kuala Lumpur, Malaysia
  • Year and Date: 2015-11-03
• [Funded Workshop] in Proceeding of the 2015 Fourth ICT International Student Project Conference (2015)
  • Place of Presentation: Tokyo University of Agriculture and Technology, Tokyo, Japan 東京都小金井市
  • Year and Date: 2015-05-23