6th International Workshop on Historical Document Imaging and Processing (HIP’21)
September 6, 2021, Lausanne, Switzerland
UPDATE 01-11-2021: The HIP’21 Proceedings are now published in the ACM Digital Library
UPDATE 03-09-2021: The full program is now online
UPDATE 03-09-2021: Due to various circumstances, HIP’21 will have to be held as an online event.
UPDATE 24-05-2021: The Call for papers is now closed for new submissions.
UPDATE 15-05-2021: The deadline for submissions has been updated:
- Full papers are due on 24 May 2021, 23:59, Timezone „Anywhere on Earth“ (AoE)
- Title and abstract MUST be submitted on 17 May 2021 via Easychair to be granted the extension
- The acceptance notification will be postponed to 4 July 2021, 1 day before the reduced early bird fee for ICDAR registration runs out
There have been increased efforts worldwide to digitize our cultural heritage conveyed in historical documents. In this workshop, we bring together researchers from various fields working on document image acquisition, restoration, analysis, indexing, and retrieval to make these documents accessible in digital libraries.
It is the sixth satellite workshop of ICDAR dedicated to this topic, following HIP’11 in Beijing, HIP’13 in Washington, HIP’15 in Nancy, HIP’17 in Kyoto and HIP’19 in Sydney that were a significant success with strong participation. HIP’21 will be held on 6 September 2021, co-located with the main ICDAR2021 Conference in Lausanne, Switzerland. Workshop attendance (virtual and on-site) requires registration for the main ICDAR conference.
HIP aims to provide the researchers with a forum that is complementary and synergetic to the main sessions at ICDAR on document analysis and recognition. The manifold topics addressed in this workshop encompass the entire processing chain from image acquisition to information extraction. We include the growing importance of machine learning in this processing chain, such as convolutional and recurrent neural networks, and we encourage the presentation of entire projects in the context of historical documents.
The workshop is planned for 1 day with 12 oral presentations. Each submission will undergo peer-review and distinguished submissions will be presented orally.
The organizers are committed to holding a safe and secure HIP’21 in the face of the current worldwide health crisis arising from COVID-19. In the event it becomes necessary, HIP’21 will be held with options for remote “virtual” participation. All accepted papers will be published in the HIP’21 proceedings, whether or not the conference takes place physically.
Submission Deadline: May 17, 2021 May 24, 2021 (Time zone: Anywhere on Earth – Tuesday May 25 12:00 noon CEST)
Acceptance Notification: June 28, 2021 July 4, 2021
Camera Ready: July 12, 2021 July 23, 2021 August 6, 2021
Workshop: September 6, 2021
Call for Papers
It is our pleasure to announce that the 6th International Workshop on Historical Document Imaging and Processing (HIP’21) will be held in conjunction with ICDAR2021, on September 5-6, 2021 in Lausanne, Switzerland.
The workshop brings together researchers working with historical documents and intends to be complementary and synergistic to the work in analysis and recognition featured in the main sessions of ICDAR, the premier international forum for researchers and practitioners in the document analysis community.
Submissions are received until May 17, 2021 May 24, 2021 (Time zone: Anywhere on Earth) via Easychair and undergo review by the members of the Program Committee. The submission of a title and abstract by May 17, 2021 via Easychair is mandatory for being granted the deadline extension!
Papers must not exceed 6 pages in length. It is not required to anonymize the submission, but authors are welcome to do so if they prefer it. Acceptance notifications will be sent out July 1, 2021.
Accepted camera-ready submissions should be sent by July 23, 2021 as PDF via email to hip2021@primaresearch.org for publication in the ACM Digital Library (see also the Proceedings of previous editions).
Authors should use the current ACM SIG Conference Proceedings Template to prepare their papers. Note that ACM has created a new LaTeX template and updated the existing Word templates. Authors also need to apply the ACM Computing Classification System (CCS) according to the ACM SIG Conference Proceedings Template.
Workshop topics include (but are not limited too):
Imaging and Image Acquisition
- Imaging for fragile materials
- Multispectral imaging
- Hyperspectral imaging
- X-Ray Fluorescence imaging
- 3D imaging
- Camera-based/non-invasive acquisition
- Case studies/applications
Digital Archiving Considerations
- Compression issues
- Measuring essential resolution (colour, spatial) and metadata
- Modelling of document image degradation
- Historical Collections
- Military records, personal journals, church records, medieval manuscripts, etc.
- Scientific, technical and educational documents
- Government archives, documents from the world cultural heritage, multi-language
Document Restoration/Improving readability
- Removing or minimizing damages, defects, ink-bleed
- Completing and filling in missing pieces based on context, prior knowledge
- Machine-learning algorithms for enhancement based on example images
- Interactive tools from a user viewpoint
- Learning from user-directed image enhancement
- Heritage documents fragment-matching
Information Extraction (within the context of historical documents)
- Content-based retrieval
- Automated or semi-automated transcription
- Machine-learning algorithms for content extraction, including recurrent neural networks, auto-encoders, and unsupervised feature learning
- Content recognition based on surrounding and supporting context
- Ontologies for modelling historical document content
Family History Documents and Genealogies
- Personal, Family, National and Historical Collections of Family Genealogy and Histories
- Extracting and linking names, dates, places, etc.
- Extracting, linking and piecing together personal and family histories and narratives
- Discovering historical social networks
Automated Classification, Grouping and Hyperlinking of Historical Documents
- Style identification (of printed text, dating or author identification)
- Searching for Documents over the Internet
- Web-based navigation within/among document images
- Search/query, retrieval, summarization or condensation of document images
- Document collecting, clustering, linking and analysis technologies
- Parallel tagging of images, transcripts, and other document layers
Digital Humanities applications of document analysis and recognition
- Computer Vision for Computational History
- Digital methods and tools for the study of historical documents
- Computational access to historical documents (e.g. Juypter notebooks)
- Workflows and pipelines for document analysis and recognition
- Crowdsourcing
For work focusing on handwriting/paleography, we recommend you have a look at IWCP2021.
General Chair
Apostolos Antonacopoulos
PRImA Research Lab
School of Science, Engineering & Environment
Newton Building
University of Salford
Greater Manchester M5 4WT
United Kingdom
a.antonacopoulos@primaresearch.org
Honorary Chair
William Barrett
Department of Computer Science
Brigham Young University
Provo, Utah 84604
USA
barrett@cs.byu.edu
Program Chairs
Maud Ehrmann
EPFL CDH DHI DHLAB
INN 116 (Bâtiment INN)
Station 14
CH-1015 Lausanne
Switzerland
maud.ehrmann@epfl.ch
Christian Clausner
PRImA Research Lab
School of Science, Engineering & Environment
Newton Building
University of Salford
Greater Manchester M5 4WT
United Kingdom
c.clausner@primaresearch.org
Organizing Chair
Clemens Neudecker
Berlin State Library
Prussian Cultural Heritage Foundation
Potsdamer Strasse 33
10785 Berlin
Germany
clemens.neudecker@sbb.spk-berlin.de
Past Organizing Chair
Stefan Pletschacher
PRImA Research Lab
School of Science, Engineering & Environment
Newton Building
University of Salford
Greater Manchester M5 4WT
United Kingdom
s.pletschacher@primaresearch.org
Program Committee
- Adi Keinan-Schoonbaert, UK
- Alicia Fornés, Spain
- Anders Hast, Sweden
- Anna Scius-Bertrand, Switzerland
- Anna-Maria Sichani, UK
- Basilis Gatos, Greece
- Beatrice Alex, UK
- Bertrand Coüasnon, France
- Christopher Kermorvant, France
- Christy Henshaw, UK
- Daniel Stoekl Ben Ezra, France
- David Smith, USA
- Dominique Stutzmann, France
- Elisa H. Barney Smith, USA
- H. Siegfried Stiehl, Germany
- Hervé Déjean, France
- Haikal El Abed, Germany
- Irina Rabaev, Israel
- Isabelle Marthot-Santaniello, Switzerland
- Jackson Reese, USA
- Jean-Philippe Moreux, France
- Jean-Yves Ramel, France
- Jihad El-Sana, Israel
- Josep Llados, Spain
- Karolina Zaczynska, Germany
- Kengo Terasawa, Japan
- Liangrui Peng, China
- Linda Studer, Switzerland
- Marco Büchler, Germany
- Maroua Mehri, Tunisia
- Masaki Nakagawa, Japan
- Michael Blumenstein, Australia
- Nicholas Howe, USA
- Peter Stokes, France
- Rafael Dueire Lins, Brazil
- Robert Sablatnig, Austria
- Roger Easton, USA
- Sally Chambers, Belgium
- Simon Clematide, Switzerland
- Simone Marinai, Italy
- Sofia Ares Oliveira, Switzerland
- Tan Lu, Belgium
- Thierry Paquet, France
- Tobias Hodel, Switzerland
- Tomo Miyazaki, Japan
- Tracy Powell, New Zealand
- Véronica Romero, Spain
- Véronique Eglin, France
- Volker Märgner, Germany
- Volkmar Frinken, USA
- Volodymyr Rybkin, Russia
- William Barrett, USA
HIP’21 Program (see also here)
| SESSION 1: Optical Character Recognition | Chair: Apostolos Antonacopoulos | |
| 09:10 | Optical Character Recognition of 19C Classical Commentaries: the current State of Affairs. (slides)
Matteo Romanello, Sven Najem-Meyer and Bruce Robertson. |
|
| 09:35 | Mixed Model OCR Training on Historical Latin Script for Out-of-the-Box Recognition and Fine-tuning. (slides)
Christian Reul, Christoph Wick, Maximilian Nöth, Andreas Büttner, Maximilian Wehner and Uwe Springmann. |
|
| 10:00 | A survey of OCR evaluation tools and metrics. (slides)
Clemens Neudecker, Konstantin Baierer, Mike Gerber, Christian Clausner, Apostolos Antonacopoulos and Stefan Pletschacher. |
|
| 10:30 | Break | |
| SESSION 2: Segmentation | Chair: Christian Clausner | |
| 11:00 | Segmentation of historical maps without annotated data. (slides)
Aurélie Lemaitre and Jean Camillerapp. |
|
| 11:25 | Text Detection and Recognition by using CNNs in the Austro-Hungarian Historical Military Mapping Survey. (slides)
Yekta Said Can and M. Erdem Kabadayi. |
|
| 11:50 | Including Keyword Position in Image-based Models for Act Segmentation of Historical Registers. (slides)
Mélodie Boillet, Martin Maarand, Thierry Paquet and Christopher Kermorvant. |
|
| 12:15-12:45: Discussion (slides) | ||
| SESSION 3: Datasets & Databases | Chair: Maud Ehrmann | |
| 14:00 | The BIR database – Identifying typographic emphasis in list-like historical documents.
Anna Scius-Bertrand, Simon Gabay, Juliette Janes, Ljudmila Petković, Caroline Corbières and Thibault Clérice. |
|
| 14:25 | Digital Peter: New Dataset, Competition and Handwriting Recognition Methods. (slides)
Mark Potanin, Denis Dimitrov, Alex Shonenkov, Vladimir Bataev, Denis Karachev and Maxim Novopoltsev. |
|
| 14:50 | GloSAT Historical Measurement Table Dataset. (slides)
Juliusz Ziomek and Stuart Middleton. |
|
| 15:30 | Break | |
| SESSION 4: Methods and Models | Chair: Matteo Romanello | |
| 16:00 | Generalized Template Matching for Semi-structured Text.
George Nagy. |
|
| 16:25 | BiblIA – a general model for Medieval Hebrew manuscripts and an open annotated dataset.
Daniel Stökl Ben Ezra, Bronson Brown-DeVost, Paweł Jabłoński, Hayim Lapin, Benjamin Kiessling and Elena Lolli. |
|
| 16:50 | Visual Analysis of Chapbooks Printed in Scotland. (slides)
Abhishek Dutta, Giles Bergel and Andrew Zisserman. |
|
| 17:15-17:30: Best paper award and wrap-up | ||
For general enquiries about HIP’21 please contact the organizers.
Copyright © HIP’21 Organizing Committee
Web hosting provided by the Berlin State Library.