Skip to main content
  • Conference proceedings
  • © 2021

Document Analysis and Recognition – ICDAR 2021

16th International Conference, Lausanne, Switzerland, September 5–10, 2021, Proceedings, Part III

Part of the book series: Lecture Notes in Computer Science (LNCS, volume 12823)

Part of the book sub series: Image Processing, Computer Vision, Pattern Recognition, and Graphics (LNIP)

Conference series link(s): ICDAR: International Conference on Document Analysis and Recognition

Conference proceedings info: ICDAR 2021.

Buy it now

Buying options

eBook USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Other ways to access

This is a preview of subscription content, log in via an institution to check for access.

Table of contents (48 papers)

  1. Front Matter

    Pages i-xix
  2. Extracting Document Semantics

    1. Front Matter

      Pages 1-1
    2. MiikeMineStamps: A Long-Tailed Dataset of Japanese Stamps via Active Learning

      • Paola A. Buitrago, Evgeny Toropov, Rajanie Prabha, Julian Uran, Raja Adal
      Pages 3-19
  3. Text and Symbol Recognition

    1. Front Matter

      Pages 37-37
    2. MRD: A Memory Relation Decoder for Online Handwritten Mathematical Expression Recognition

      • Jiaming Wang, Qing Wang, Jun Du, Jianshu Zhang, Bin Wang, Bo Ren
      Pages 39-54
    3. Full Page Handwriting Recognition via Image to Sequence Extraction

      • Sumeet S. Singh, Sergey Karayev
      Pages 55-69
    4. SPAN: A Simple Predict & Align Network for Handwritten Paragraph Recognition

      • Denis Coquenet, Clément Chatelain, Thierry Paquet
      Pages 70-84
    5. IHR-NomDB: The Old Degraded Vietnamese Handwritten Script Archive Database

      • Manh Tu Vu, Van Linh Le, Marie Beurton-Aimar
      Pages 85-99
    6. Sequence Learning Model for Syllables Recognition Arranged in Two Dimensions

      • Valerii Dziubliuk, Mykhailo Zlotnyk, Oleksandr Viatchaninov
      Pages 100-111
    7. Transformer for Handwritten Text Recognition Using Bidirectional Post-decoding

      • Christoph Wick, Jochen Zöllner, Tobias Grüning
      Pages 112-126
    8. Zero-Shot Chinese Text Recognition via Matching Class Embedding

      • Yuhao Huang, Lianwen Jin, Dezhi Peng
      Pages 127-141
    9. Text-Conditioned Character Segmentation for CTC-Based Text Recognition

      • Ryohei Tanaka, Kunio Osada, Akio Furuhata
      Pages 142-156
    10. Towards Fast, Accurate and Compact Online Handwritten Chinese Text Recognition

      • Dezhi Peng, Canyu Xie, Hongliang Li, Lianwen Jin, Zecheng Xie, Kai Ding et al.
      Pages 157-171
    11. HCADecoder: A Hybrid CTC-Attention Decoder for Chinese Text Recognition

      • Siqi Cai, Wenyuan Xue, Qingyong Li, Peng Zhao
      Pages 172-187
    12. Meta-learning of Pooling Layers for Character Recognition

      • Takato Otsuzuki, Heon Song, Seiichi Uchida, Hideaki Hayashi
      Pages 188-203
  4. Document Analysis Systems

    1. Front Matter

      Pages 205-205
    2. Text-line-up: Don’t Worry About the Caret

      • Chandranath Adak, Bidyut B. Chaudhuri, Chin-Teng Lin, Michael Blumenstein
      Pages 207-222
    3. Multimodal Attention-Based Learning for Imbalanced Corporate Documents Classification

      • Ibrahim Souleiman Mahamoud, Joris Voerman, Mickaël Coustaty, Aurélie Joseph, Vincent Poulain d’Andecy, Jean-Marc Ogier
      Pages 223-237
    4. Light-Weight Document Image Cleanup Using Perceptual Loss

      • Soumyadeep Dey, Pratik Jawanpuria
      Pages 238-253

About this book

This four-volume set of LNCS 12821, LNCS 12822, LNCS 12823 and LNCS 12824, constitutes the refereed proceedings of the 16th International Conference on Document Analysis and Recognition, ICDAR 2021, held in Lausanne, Switzerland in September 2021. The 182 full papers were carefully reviewed and selected from 340 submissions, and are presented with 13 competition reports.

The papers are organized into the following topical sections: extracting document semantics, text and symbol recognition, document analysis systems, office automation, signature verification, document forensics and provenance analysis, pen-based document analysis, human document interaction, document synthesis, and graphs recognition.

Editors and Affiliations

  • Universitat Autònoma de Barcelona, Barcelona, Spain

    Josep Lladós

  • Lehigh University, Bethlehem, USA

    Daniel Lopresti

  • Kyushu University, Fukuoka-shi, Japan

    Seiichi Uchida

Bibliographic Information

Buy it now

Buying options

eBook USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Other ways to access