• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Enhancement of handwritten mathematical expression recognition through establishment of multi-dimensional structural analysis

Research Project

Project/Area Number 19H01117
Research Category

Grant-in-Aid for Scientific Research (A)

Allocation TypeSingle-year Grants
Section一般
Review Section Medium-sized Section 61:Human informatics and related fields
Research InstitutionTokyo University of Agriculture and Technology

Principal Investigator

Nakagawa Masaki  東京農工大学, 学内共同利用施設等, 特任教授 (10126295)

Co-Investigator(Kenkyū-buntansha) NGUYENTUAN CUONG  東京農工大学, 工学(系)研究科(研究院), 特任助教 (10814246)
Project Period (FY) 2019-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥37,830,000 (Direct Cost: ¥29,100,000、Indirect Cost: ¥8,730,000)
Fiscal Year 2022: ¥9,620,000 (Direct Cost: ¥7,400,000、Indirect Cost: ¥2,220,000)
Fiscal Year 2021: ¥8,060,000 (Direct Cost: ¥6,200,000、Indirect Cost: ¥1,860,000)
Fiscal Year 2020: ¥9,880,000 (Direct Cost: ¥7,600,000、Indirect Cost: ¥2,280,000)
Fiscal Year 2019: ¥10,270,000 (Direct Cost: ¥7,900,000、Indirect Cost: ¥2,370,000)
Keywords手書き数式認識 / 構造解析 / 文脈処理 / 深層ニューラルネットワーク / アテンション
Outline of Research at the Start

本研究では,手書き数式認識の文脈処理(幾何学的,言語的,及び,ある程度の意味的な文脈を内包)と構造認識を高めるために,ゲート付きの再帰ニューラルネットワークの2次元化,複数の部分構造にアテンションを払うend-to-endのDNN,数式全体を複数のマルコフ確率場で覆ってコスト最小化を求める方法の3つを試み,これらの最適な統合も目指す.ここで提案する方式は2次元の手書き数式認識に特化した方法でないことから,手書き数式認識を包含して,より包括的な構造解析的パターン認識の進展を阻んできたノイズを含む多次元構造あるいはグラフ構造の曖昧性解消に資することを目指す.

Outline of Final Research Achievements

This research aimed to recognize handwritten mathematical expressions, where ambiguities occurs in symbol segmentation, symbol identification, and positional relationship identification. Context processing is difficult unlike natural languages due to the lack of redundancy. This research clarified that it is superior to learn geometric context implicitly by Deep Neural Networks and evaluate language context explicitly by a language model. Specifically, an encoder/decoder model that pays attention to multiple substructures, semi-supervised learning that compensates for the lack of labeled learning patterns, and weighting the evaluation function with language context improved recognition performance. Furthermore, a method was proposed to artificially generate learning patterns, which were availed for an international recognition contest.

Academic Significance and Societal Importance of the Research Achievements

手書き数式認識は,構造解析的パターン認識の典型的問題であり,本研究成果は,その進展を阻んできたノイズを含む多次元構造解析の曖昧性解消に資する.また,本研究により,手書きによる数式解答の答合せや,数式解答の自動採点・採点支援の土台ができた.自動採点は,受験者が自分の答案に対する採点を確認し,誤採点があれば照会できる仕組みを前提に,機械が手書き認識と採点を行って受験者に返す.採点結果を即時に受験者に返して復習を促すことができ,採点の労力を軽減できる.採点支援には,解答を事前に機械採点やクラスタリングし,また,採点の注意点を明確にすることで,採点者による誤った採点やばらつきを防止できる.

Report

(6 results)
  • 2022 Annual Research Report   Final Research Report ( PDF )
  • 2021 Annual Research Report
  • 2020 Annual Research Report
  • 2019 Comments on the Screening Results   Annual Research Report
  • Research Products

    (24 results)

All 2023 2022 2021 2020 2019 Other

All Int'l Joint Research (1 results) Journal Article (5 results) (of which Peer Reviewed: 5 results,  Open Access: 3 results) Presentation (18 results) (of which Int'l Joint Research: 17 results)

  • [Int'l Joint Research] Jagiellonian University(ポーランド)

    • Related Report
      2019 Annual Research Report
  • [Journal Article] Syntactic data generation for handwritten mathematical expression recognition2022

    • Author(s)
      [2]Thanh-Nghia Truong, Cuong Tuan Nguyen, and Masaki Nakagawa
    • Journal Title

      Pattern Recognition Letters

      Volume: Vol. 153 Pages: 83-91

    • DOI

      10.1016/j.patrec.2021.12.002

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Clustering of Handwritten Mathematical Expressions for Computer-Assisted Marking2021

    • Author(s)
      Vu tran minh KHUONG,Khanh Minh PHAN, Huy Quang UNG, Cuong Tuan NGUYEN, Masaki NAKAGAWA
    • Journal Title

      IEICE Transactions on Information and Systems

      Volume: E104.D Issue: 2 Pages: 275-284

    • DOI

      10.1587/transinf.2020EDP7087

    • NAID

      130007979511

    • ISSN
      0916-8532, 1745-1361
    • Year and Date
      2021-02-01
    • Related Report
      2020 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Clustering online handwritten mathematical expressions2021

    • Author(s)
      Ung Huy Quang、Nguyen Cuong Tuan、Phan Khanh Minh、Khuong Vu Tran Minh、Nakagawa Masaki
    • Journal Title

      Pattern Recognition Letters

      Volume: 146 Pages: 267-275

    • DOI

      10.1016/j.patrec.2021.03.027

    • Related Report
      2021 Annual Research Report 2020 Annual Research Report
    • Peer Reviewed
  • [Journal Article] A CNN based Localization and Classification Features for Clustering Offline Handwritten Mathematical Expression2020

    • Author(s)
      Cuong Tuan Nguyen, Vu Tran Minh Khuong, Hung Tuan Nguyen, Masaki Nakagawa
    • Journal Title

      Pattern Recognition Letters

      Volume: Vol. 131 Pages: 113-120

    • DOI

      10.1016/j.patrec.2019.12.015

    • Related Report
      2019 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Pattern Generation Strategies for Improving Recognition of Handwritten Mathematical Expressions2019

    • Author(s)
      Anh Duc Le, Bipin Indurkhya , Masaki Nakagawa
    • Journal Title

      Pattern Recognition Letters,

      Volume: Vol. 128, Pages: 255-262

    • DOI

      10.1016/j.patrec.2019.09.002

    • Related Report
      2019 Annual Research Report
    • Peer Reviewed / Open Access
  • [Presentation] A Semi-Supervised Learning Framework using Mixed Augmentations and Scheduled Pseudo-Label Loss for Handwritten Text Recognition2023

    • Author(s)
      Masayuki Honda, Hung Tuan Nguyen, Cuong Tuan Nguyen, Cong Kha Nguyen, Ryosuke Odate, Takashi Kanemaru and Masaki Nakagawa
    • Organizer
      IEICE technical report (電子情報通信学会信学技法), PRMU2022-97
    • Related Report
      2022 Annual Research Report
  • [Presentation] オンラインLMSのための手書き入力CBTの設計と実装2022

    • Author(s)
      矢嶋遼,安野史子,中川正樹,清水郁子
    • Organizer
      EICE technical report, ET2021-45(2022-01), pp.13-18 (2022.1).
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Visual Constraints for Generating Multi-Domain Offline Handwritten Mathematical Expressions2022

    • Author(s)
      [12]Huy Quang Ung, Hung Tuan Nguyen, Cuong Tuan Nguyen, Tsunenori Ishioka and Masaki Nakagawa
    • Organizer
      IEICE Technical Report, PRMU2021-69 (2022-03), pp.54-59 (2022.3).
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] オンライン手書き数式認識のための文脈自由文法における木構造解析2022

    • Author(s)
      北嶋完基,グエン トゥアン クーン,清水郁子,中川正樹
    • Organizer
      IEICE Technical Report, PRMU2021-76 (2022-03), pp.103-108 (2022.3).
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] GSSF: A Generative Sequence Similarity Function based on a Seq2Seq model for clustering online handwritten mathematical answers2021

    • Author(s)
      Huy Quang Ung, Cuong Tuan Nguyen, Hung Tuan Nguyen and Masaki Nakagawa
    • Organizer
      16th International Conference on Document Analysis and Recognition, Lausanne, Switzerland
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 2D Self-Attention Convolutional Recurrent Network for Offline Handwritten Text Recognition2021

    • Author(s)
      Nam Tuan Ly, Hung Tuan Nguyen and Masaki Nakagawa
    • Organizer
      16th International Conference on Document Analysis and Recognition, Lausanne, Switzerland
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Global Context for Improving Recognition of Online Handwritten Mathematical Expressions2021

    • Author(s)
      Cuong Tuan Nguyen, Thanh-Nghia Truong, Hung Tuan Nguyen and Masaki Nakagawa
    • Organizer
      16th International Conference on Document Analysis and Recognition, Lausanne, Switzerland
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] A Transformer-based Math Language Model for Handwritten Math Expression Recognition2021

    • Author(s)
      Huy Quang Ung, Cuong Tuan Nguyen, Hung Tuan Nguyen, Thanh-Nghia Truong and Masaki Nakagawa
    • Organizer
      1st Workshop on Document Images and Language (DIL 2021), Lausanne, Switzerland
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Relation-based Representation for Handwritten Mathematical Expression Recognition2021

    • Author(s)
      Thanh-Nghia Truong, Huy Quang Ung, Hung Tuan Nguyen, Cuong Tuan Nguyen and Masaki Nakagawa
    • Organizer
      14th Workshop on Graphics Recognition (GREC 2021), Lausanne, Switzerland
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Temporal Classification Constraint for Improving Handwritten Mathematical Expression Recognition2021

    • Author(s)
      Cuong Tuan Nguyen, Hung Tuan Nguyen, Kei Morizumi and Masaki Nakagawa
    • Organizer
      3rd Workshop on Machine Learning (WML 2021), Lausanne, Switzerland
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] A Self-Attention based Model for Offline Handwritten Text Recognition2021

    • Author(s)
      Nam Tuan Ly, Trung Tan Ngo and Masaki Nakagawa
    • Organizer
      6th Asian Conference on Pattern Recognition (ACPR 2021), Jeju, South Korea, (2021.11)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Learning Symbol Relation Tree for Online Handwritten Mathematical Expression Recognition2021

    • Author(s)
      Thanh-Nghia Truong, Cuong Tuan Nguyen, Hung Tuan Nguyen, and Masaki Nakagawa
    • Organizer
      6th Asian Conference on Pattern Recognition (ACPR 2021), Jeju, South Korea, (2021.11)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Online Handwritten Mathematical Symbol Segmentation and Recognition with Bidirectional Context2020

    • Author(s)
      Cuong Tuan Nguyen, Thanh-Nghia Truong, Huy Quang Ung and Masaki Nakagawa
    • Organizer
      ICFHR
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Evaluation of Secure Pad Resilient to Shoulder Hacking2020

    • Author(s)
      Kokoro Kobayashi , Tsuyoshi Oguni, and Masaki Nakagawa
    • Organizer
      HCII 2020
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Improvement of End-to-End Offline Handwritten Mathematical Expression Recognition by Weakly Supervised Learning2020

    • Author(s)
      Thanh-Nghia Truong, Cuong Tuan Nguyen, Khanh Minh Phan, and Masaki Nakagawa
    • Organizer
      ICFHR
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Generating Synthetic Handwritten Mathematical Expressions from a LaTeX Sequence or a MathML Script2019

    • Author(s)
      Minh Khanh Phan, Tran Minh Khuong Vu, Quang Huy Ung, Masaki Nakagawa
    • Organizer
      Proc. of ICDAR
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Interactive Interfaces for Recognizing Online Handwritten Mathematical Expressions and Correcting Misrecognitions2019

    • Author(s)
      Vu Tran Minh Khuong, Minh Khanh Phan and Masaki Nakagawa
    • Organizer
      Proc. 2nd International Workshop on Open Services and Tools for Document Analysis (ICDAR-OST)
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Strategy and Tools for Collecting and Annotating Handwritten Descriptive Answers for Developing Automatic and Semi-Automatic Marking - an Initial Effort to Math2019

    • Author(s)
      Quang Huy Ung, Minh Khanh Phan and Masaki Nakagawa
    • Organizer
      Proc. 2nd International Workshop on Open Services and Tools for Document Analysis (ICDAR-OST)
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research

URL: 

Published: 2019-04-18   Modified: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi