IAPR TC11 Newsletter 2021 07
Click on the buttons below to view sections of the newsletter.
- Message from the Editor
- Dates and Deadlines
- Upcoming Conferences and Events
- ICDAR 2021
- IAPR/ICDAR Awards
- ICDAR 2021: Keynote Speakers *(repost)*
- ICDAR 2021: COVID Situation *(repost)*
- Summer School
- 4th IAPR TC 10/11 Summer School on Document Analysis *(repost)*
- Call for Papers: 20th Conference of the International Graphonomics Society (IGS 2021)
- IRISA/INSA Rennes (France): Research Engineer/PostDoc Position (2.5 Years)
- TC11 Datasets Repository *(repost)*
Dear TC11 members,
With the COVID situation in Switzerland unchanged, we are looking forward to a hybrid ICDAR 2021 conference, which will be held from September 5-10 in Lausanne, Switzerland. In the context of the hybridization, additional presentation materials have to be uploaded by authors of the main conference early August. With nearly 500 registrations so far, including about 200 on-site registrations, ICDAR 2021 will provide an ideal forum during one week for scientists and practitioners involved in document analysis and recognition to exchange and discuss their latest research. The detailed program of the main conference is available online.
The ICDAR 2021 conference will be opened by the keynote talks given by the recipients of the IAPR/ICDAR awards, Prof. Masaki Nakagawa (IAPR/ICDAR Outstanding Achievement Award) and Mickaël Coustaty (IAPR/ICDAR Young Investigator Award). Congratulations to the recipients!
Looking further ahead, this newsletter also includes the first call for papers for the 20th Conference of the International Graphonomics Society (IGS 2021), which was postponed to be held on-site from June 7-9, 2022, in Las Palmas de Gran Canaria, Spain.
Interested in a PostDoc position related to document analysis and recognition? The careers section includes an opportunity at IRISA/INSA Rennes, France.
Andreas Fischer, TC11 Communications Officer
( firstname.lastname@example.org )
- August 5 Teaser video and presentation document submission ICDAR 2021
- August 15 Online oral presentation video submission ICDAR 2021
- January 8 Paper submission IGS 2021
Upcoming Conferences and Events
2022 and Later
- IGS 2021. Las Palmas de Gran Canaria, Spain (June 7-9, 2022)
- ICFHR 2022. Hyderabad, India (December, 2022)
The IAPR/ICDAR Award Program is an established program designed to recognize individuals who have made outstanding contributions to the field of Document Analysis and Recognition in one or more of the following areas:
- Training of students
- Research/Industry interaction
- Service to the community
Every two years, two award categories are presented. Namely, the IAPR/ICDAR Young Investigator Award (less than 40 years old at the time the award is made), and the IAPR/ICDAR Outstanding Achievements Award. Each award consists of a token gift and a suitably inscribed certificate.
Both recipients of the IAPR/ICDAR awards will be invited to give a keynote speech to open the ICDAR 2021 conference. The recipients are:
- Prof. Masaki Nakagawa (IAPR/ICDAR Outstanding Achievement Award) for his outstanding contributions in online handwriting beyond the Latin Alphabet, early integration of handwriting recognition in practically useful systems, and his excellent contributions for the ICDAR community, connecting us with Industry in Asia.
- Mickaël Coustaty (IAPR/ICDAR Young Investigator Award) for his notable contributions in developing systems for historical documents processing and his dedicated commitment to the document analysis community.
Jean-Christophe Burie and Faisal Shafait
TC10 and TC11 Chairs
ICDAR 2021: Keynote Speakers (repost)
Speaker 1: Prem Natarajan
OCR: A Journey through Advances in the Science, Engineering, and Productization of AI/ML
From the very early years of AI, the problem of optical character recognition (OCR) has captured the imagination of researchers; Selfridge and Neisser presented an approach for OCR of hand printed characters in 1960. During last three decades, optical character recognition (OCR) technology for machine printed and handwritten text has evolved in significant ways – from script-specific techniques to script-independent methodologies, and from segmentation-based techniques to hidden Markov models to deep learning. In my talk, I will present my perspective on that evolution and it’s interplay with concomitant advances in speech recognition, natural language processing, and computer vision. The presentation will include a discussion of some practical, even if off the beaten path, applications of OCR technology, including work done in partnership with the census bureau in applying a deep learning based OCR framework to census forms. I will also share my views on some of the most interesting open problems in the field of OCR and document processing. The presentation will conclude with a few comments about one of my current areas of research interests – fairness in AI and machine learning.
Prem Natarajan is a Vice President at Amazon where he leads research and engineering efforts in dialog systems, natural language understanding, and multimodal/multimedia technologies in the Alexa AI organization. Prior to joining Amazon in June 2018, he was with the University of Southern California (USC) where he was Senior Vice Dean of Engineering in the Viterbi School of Engineering, Executive Director of the Information Sciences Institute (a 300-person R&D organization), and Research Professor of computer science with distinction. Prior to that, as Executive VP and Principal Scientist at Raytheon BBN Technologies, he led the speech, language, and multimedia business unit, which included research and development operations, and commercial products for real-time multimedia monitoring, document analysis, and information extraction. During his tenure at USC and at BBN, Natarajan directed R&D efforts in speech recognition, natural language processing, computer vision, and other applications of machine learning. While at USC, he led nationally influential DARPA and IARPA sponsored research efforts in biometrics/face recognition, OCR, NLP, media forensics, and forecasting. Most recently at Amazon, he helped to launch the Fairness in AI (FAI) program – a collaborative effort between NSF and Amazon for funding fairness focused research efforts in US Universities.
Speaker 2: Beáta Megyesi
Cracking Ciphers with “AI-in-the-loop”: Transcription and Decryption in a Cross-Disciplinary Field
Accurate transcription of hand-written texts in images is indispensable in many research areas in digital humanities. Manual transcription is error-prone, time-consuming, and expensive to produce. Historical texts with their specific textual qualities require expert knowledge and trained eyes. During the past years, image processing applied to hand-written historical text documents to provide transcription output has been shown great opportunities, but also challenges for users. How can users without knowledge in AI in general and HTR in particular transcribe hand-written documents efficiently with ”AI-in-the- loop”? In my talk, I will focus on encrypted manuscripts from Early Modern times with various symbols systems, hand-writing styles, and languages. The point of departure is the DECRYPT project, aiming at the creation of resources and tools for historical cryptology by bringing the expertise of various disciplines together for collecting images of ciphers and keys, to transcribe them, and to decrypt and contextualize those. I will give an overview of the project, the methods we use to solve various problems from transcription to decryption including historical corpora and natural language processing methods.
Beáta Megyesi is a professor of computational linguistics at Uppsala University, the former head of department at the Dept. Linguistics and Philology, Uppsala University, Sweden, and the current president of the North European Association for Language Technology (NEALT). She is specialized in digital philology and natural language processing with a special interest in the automatic analysis of non-standard, noisy language data, from text produced by language learners to historical texts and encrypted documents. She has been participating in ten externally funded, cross-disciplinary research projects and currently serves as the PI of the DECRYPT project, financed by the Swedish Research Council (grant 2018-06074). Bea received her Ph.D. in speech communication from the Royal Institute of Technology (KTH) in Stockholm, Sweden.
ICDAR 2021: COVID Situation (repost)
Swiss COVID Regulations
The following websites are regularly updated by the government:
What does it mean for ICDAR?
The current COVID situation in Switzerland allows to hold ICDAR 2021 in person. A hybrid mode is setup with both on-site and online participants. It is recommended to register for on-site participation if you plan to attend the conference in person. Should it become necessary to limit on-site participation to scientific and/or social events, the date of payment of the registration fee will be taken into account, following the “first come, first serve” principle. If travel is not possible due to COVID-related restrictions, a downgrade to online participation will be applied, refunding the difference in the registration fees.
Current COVID measures envisaged for ICDAR 2021
Wearing masks when indoors. We are observing the evolution of the COVID certificate (fully vaccinated, recovered from COVID, or tested negativ) but do not impose it for the conference at the moment.
4th IAPR TC 10/11 Summer School on Document Analysis (repost)
Theme: Digital Transformation in a changing world
Dates: 23rd to 27th of August 2021
Location: Lulea University of Technology, Sweden
Endorsed by the IAPR TC-10 (Technical Committee on Graphics Recognition) and TC-11 (Reading Systems).
The 4th IAPR Summer School on Document Analysis is a premier annual summer school focused on recent developments in document analysis. It is gathering leading researchers and scientists in emerging areas of document analysis to give in-depth and objective exposure to the participants.
We are announcing that SSDA 2021 will take place in HYBRID FORM. A very unique aspect of this summer school will be the novel hybridization concept, allowing participants from all areas (depending on the current Corona restrictions) to participate either virtually, or physically in Luleå. We build on our long-standing experience in distance education and conferences in Luleå and the northern region following pedagogical principals of effective teaching and learning.
The objective of the school is to provide the participants with different aspects related to digital transformation of documents and beyond. All the latest research being carried out in the field of document understanding, document (image) analysis, natural scene text detection and recognition, historical document analysis, Corona and Virtualization, and new topics will be covered in the school.
The summer school will provide a great opportunity to participants to expand their knowledge and skills by linking the theory with the real implementation. Speakers from different areas of expertise will be invited to enrich the overall impact of the school. By the end of the school participants will have advanced knowledge and application experience in:
- Applied AI in document analysis
- Document analysis for business applications
- Natural scene text detection
- Complex document understanding
- Historical document processing
- Current challenges in the field of document analysis
- Contribution of major stakeholders in this field
- Corona and Virtualization.
- Expert’s talks on document understanding, document (image) analysis, natural scene text detection and recognition, historical document analysis, Corona and Virtualization, and other new topics.
- Field experts will provide tutorial-based lectures and hands-on laboratory sessions
- Partial scholarships for selected International students
- Hackathon Competition
Registration info here.
Call for Papers: 20th Conference of the International Graphonomics Society (IGS 2021)
Conference Title: Intertwining Graphonomics with Human Movements Conference Venue: Museo Elder, Las Palmas de Gran Canaria, Spain
Conference Dates: June 7-9, 2022 (On-site)
Deadline for Submissions: January 8, 2022
First Call for Papers
We are pleased to announce the twentieth edition of the biennial conference of the International Graphonomics Society that will take place from 7 to 9 June 2022 in the “Elder museum of science and technology” in Las Palmas de Gran Canaria, Spain. The overall objective of this conference is to provide a single track space of discussion about the graphonomic impact trends in other skilled human movements and vice versa. To this aim, IGS2021 is intended to be a stimulating conference to encourage research and discussion from an interdisciplinary point of view.
Topics of interest (but not limited to) are:
- Handwriting generation, analysis and recognition
- Biometrics: writer identification and signature verification
- Symbol, Equation, Sketch and Drawing
- Human Computer Interaction
- Sports movements assessment
- Medical applications
- Forensic applications
- Cultural Heritage applications
- Large digital archives
- 2D/3D Kinematics analysis
- Creativity, cognitive and brain-inspired art
Authors are invited to submit original contributions. Guidelines for submission and camera ready format are available on the website: https://www.graphonomics.net/igs2021
IRISA/INSA Rennes (France): Research Engineer/PostDoc Position (2.5 Years)
Optical Music Recognition System for Historical Orchestra Scores
October 1, 2021 - May 31, 2024 Contract period
IRISA - Intuidoc
IRISA is a joint research center for Informatics, including Robotics and Image and Signal Processing. 850 people, 40 teams, explore the world of digital sciences to find applications in healthcare, ecology-environment, cyber-security, transportation, multimedia, and industry. INSA Rennes is one of the 8 trustees of IRISA.
The Intuidoc team (https://www.irisa.fr/intuidoc) conducts research on the topic of document image recognition. Since many years, the team proposes a system, called DMOS-PI method, for document structure analysis of documents. This DMOS-PI method is used for document recognition, or field extraction in archive documents, handwritten contents damaged documents (musical scores, archives, newspapers, letters, electronic schema, etc.).
Collabscore is a project founded by ANR (French Research National Agency), led by the CNAM. The goal is to study ancient scores provided by the BNF (Bibliothèque National de France) and Royaumont foundation. Collabscore is a multidisciplinary project. The first task consists in improving OMR (Optical Music Recognition) results using learning techniques. The second action will focus on methods for automatic alignment of the scored score with other multimodal sources. The last one will set up demonstrators based on notated scores at two of the project partners, representative, in various ways, of institutions in charge of musical heritage collections (BnF and Fondation Royaumont). Intuidoc team focuses on the first task of musical score recognition.
Position to be filled
- Position: Post-doctoral fellow / Research Engineer
- Time commitment: Full-time
- Duration of the contract: up to 32 months, starting as soon a possible
- Supervisors: Bertrand Coüasnon, Aurélie Lemaitre, Yann Soullard
- Indicative salary: Up to €36 000 gross annual salary (according to experience), with social security benefits
- Location: IRISA - Rennes, France
The post-doctoral/engineer fellow will work on the conception of a OMR system. Based on previous works of our research team, the goal of this position is to enrich an existing system (DMOS-PI) to get a complete OMR system for historical orchestra scores. The tasks are mainly:
- define a grammatical description of musical notation, using the existing DMOS-PI method;
- generate unsupervised data for training musical symbols recognizers;
- create a gradual mechanism for adapting the system to new partitions;
- integrate anomaly detection into the system.
Logical programming from grammars and languages is expected in this work. Machine Learning methods, especially Deep learning-based approaches, will be used to solve some of the tasks, as done in our previous works on music symbol detection.
- PhD, Master degree or Engineering degree in computer science
- Experience in document recognition or statistical analysis.
- Skills in grammars and languages and/or logical programming are nice-to-have, as well as knowledge of music notation.
- Knowledge in deep learning with an experience with at least one library dedicated to deep learning (Keras, Tensorflow, Pytorch) are expected.
Bertrand Coüasnon, Director, Media and Interactions Department (IRISA)
TC11 Datasets Repository (repost)
TC11 maintains a collection of datasets that can be found online in the TC11 Datasets Repository.
If you have new datasets (e.g., from competitions) that you wish to share with the research community, please use the online upload form. For questions and support, please contact the TC11 Dataset Curator (contact information is below).
Joseph Chazalon (TC11 Dataset Curator)
( email@example.com )
Call for Contributions: To contribute news items, please send a short email to the editor, Andreas Fischer (). Contributions might include conference and workshop announcements/updates/reports, career opportunities, book reviews, or anything else of interest to the TC-11 community.
Subscription: This newsletter is sent to subscribers of the IAPR TC11 mailing list. To join the TC-11 mailing list, please click on this link: Join the TC-11 Mailing List. To manage your subscription, please visit the mailing list homepage: TC-11 Mailing List Homepage.