[IAPR-TC10] Newsletter 151 – May 2022

Welcome to the May edition of the TC10 newsletter.

In this issue, you will find the last call for participation for DAS 2022, ICFHR call for workshops, tutorials and competitions, a selection of workshop in conjunction of ECCV and ICPR conferences and a call for paper in a special issue of Pattern Recognition Letters journal: Advances and New challenges in Document Analysis, processing and Recognition at the Dematerialization Age. In addition, the in Memoriam of Professor Sargur N. Srihari from the IAPR newsletter.

I hope to see you soon in La Rochelle,

Christophe Rigaud
IAPR-TC10 Communications Officer

Call for contributions: feel free to contribute to TC10 newsletters, by sending any relevant news, event, notice, open position, dataset or link to us on iapr.tc10[at]gmail.com

1) Upcoming deadlines and events


  • Deadlines:
    • May 22, paper abstract submission deadline ICFHR 2022
    • May 31, workshop & tutorial proposal deadline ICFHR 2022
    • June 5, competition proposal deadline ICFHR 2022
    • June 6, paper submission deadline MANPU 2022extended
  • Events:
    • May 22-25, conference DAS 2022, La Rochelle, France
    • June 1-3, conference ICPRAI 2022, Paris, France
    • July 10-16, summer school ICVSS, Italy (Sicily)
    • August 21, workshop MANPU 2022, Montréal, Québec (QC), Canada
    • August 21-25, conference ICPR 2022, Montréal, Québec (QC), Canada
    • October 16-19, conference ICIP 2022, Bordeaux, France
    • October 23-27, conference ECCV 2022, Tel Aviv, Israël
    • December 2022, conference ICFHR 2022, Hyderabad, India

2023 and later

  • Events:
    • August 2023, conference ICDAR 2023, San José, California, USA
    • September 2024, conference ICDAR 2024, Athens, Greece

2) 📢 DAS 2022 Last call for participation

15th IAPR International Workshop on Document Analysis Systems (DAS 2022)

May 22-25, La Rochelle, France
DAS 2022 participation will be hybrid (i.e., both in-person and online)


🎟️ Registration for DAS 2022 is open. Complete information about the scientific program, tutorials, and keynote talks is now available online, and summarized below.

ℹ️ About DAS

DAS 2022 is the 15th edition of the IAPR sponsored workshop focusing on system-level issues and approaches for document analysis and recognition. The workshop consists of invited keynote speeches, oral and poster paper presentations, tutorials, and working group discussions.

Accepted Papers. The accepted papers at DAS 2022 cover a wide range of topics, including Image Processing, OCR, HTR, Forensics, Historical Document Analysis, Natural Language Processing, Information Retrieval, Deep Learning, and Datasets and Evaluation.

A Quick Summary of Paper Submissions and Acceptances:

  • 88 full-length papers were submitted for DAS 2022
    • 31 were accepted for an oral presentation, and
    • 21 for a poster presentation.
  • 16 short papers were also submitted to DAS 2022, and accepted for poster presentation.

🏖️ Location

DAS 2022 will be hosted by La Rochelle University (France) on May 22-25, 2022. The city of La Rochelle, situated on the central west coast of France, possesses a rich historical fabric including the Saint-Nicolas tower and urban heritage. In the early 21st century, the city has consistently been ranked among France’s most liveable cities.

🎤 Keynotes and Tutorials

  • Keynote 1: “Automatic Question Answering & Generation in News Archives” by Professor Adam Jatowt (University of Innsbruck, Austria)
  • Keynote 2: “The kiss of the Prince”: Bringing Document Content to Life by Professor Andreas Dengel (German Research Center for Artificial Intelligence (DFKI) in Kaiserslautern, Germany)
  • Tutorial: “Unlocking the Potential of Unstructured Data in Finance Through Document Intelligence” by Himanshu Sharad Bhatt (Research Director at American Express AI Labs, India)

📑 Program, Registration and Participation (In-Person and Online)

Final scientific program is available at: https://das2022.univ-lr.fr/index.php/scientific-program-overview/

Please register at: https://das2022.univ-lr.fr/index.php/registration-2/

For discounted accommodation options, please see: https://das2022.univ-lr.fr/index.php/accommodation/

For information on traveling to La Rochelle, please see: https://das2022.univ-lr.fr/index.php/on-site-participation/

For remote/online participation information, please see: https://das2022.univ-lr.fr/index.php/online-participation/

3) Call for paper MANPU 2022 – deadline extended

5th International Workshop on coMics ANalysis, Processing and Understanding

August 21, 2022, Montreal, Canada
In conjunction with ICPR 2022

Comics is a medium constituted of images combined with text and other visual information in order to narrate a story. Nowadays, comic books are a widespread cultural expression all over the world. The market of comics continues to grow, for example, the market in Japan is about 4.25 billion USD in 2015. Moreover, from the research point of view, comics images are attractive targets because the structure of a comics page includes various elements (such as panels, speech balloons, captions, leading characters, and so on), the drawing of which depends on the style of the author and presents a large variability. Therefore comics image analysis is not a trivial problem and is still immature compared with other kinds of image analysis.

Important dates

Title and abstract submission due: June 6, 2022

Paper submission due: May 13 June 6, 2022

Notification of acceptance: May 31 June 30, 2022

Camera-ready paper due: June 6 September 2, 2022

Workshop: August 21, 2022

Scope and Topics

The scope of this workshop includes, but is not limited to,

– Comics Image Processing
– Comics Analysis and Understanding
– Comics Recognition
– Comics Retrieval and Spotting
– Comics Enrichment
– Born Digital Comics
– Reading Behavior Analysis of Comics
– Comics Generation
– Copy protection
– Fraud detection
– Physical/Digital Comics Interfaces
– Cognitive Processing and Comprehension of Comics
– Linguistics Analysis of Comics


To evaluate the proposed works, participants will be able to use the following datasets that are publicly available. Researchers can request to download them at each website.

– eBDtheque consists of 100 images with ground truth for panels, speech balloons, tails, text lines, leading characters: http://ebdtheque.univ-lr.fr/

– Manga109 consists of over 20 thousand images of 109 volumes (21,142 images): http://www.manga109.org/en/

Paper Submissions

Submission and Review

All papers will have to be submitted through the EasyChair submission system on or before the submission deadline. Authors can update their papers before the submission deadline. MANPU 2022 will follow a single-blind review process.

Papers should be formatted with the style files/details available at Information for Authors of Springer Computer Science Proceedings. Only PDF files are accepted. A complete paper should be submitted in the proper format. Only Full paper (12-15 pages) is accepted.

See more information on the website :   https://manpu2022.imlab.jp/

General Co-Chairs

Jean-Christophe Burie (France)

Motoi Iwata (Japan)

Miki Ueno (Japan)

Program Co-Chairs

Rita Hartel (Germany)

Ryosuke Yamanishi (Japan)

Tien-Tsin Wong (Hong Kong)

Advisory Board

Kiyoharu Aizawa (Japan)

Koichi Kise (Japan)

Jean-Marc Ogier (France)

Toshihiko Yamasaki (Japan)

More info: https://manpu2022.imlab.jp

4) Call for Workshops & Tutorials ICFHR 2022

The ICFHR Organizing Committee invites proposals for workshops/tutorials that will be held on December 7, 2022, in Hyderabad, India. Researchers interested in organizing workshops or tutorials at ICFHR 2022 are invited to submit a proposal. The broad area of the submitted proposals for the workshop and tutorials could be topics of interest to ICFHR or the document image understanding and reading systems (that fall under the broad scope of TC10/TC11 of IAPR). The tutorial can be organized on topics of recent trends and tools used in the community. The proposal shall include the following information in a single PDF file:

Technical Information

  • Workshop/Tutorial title.
  • Topics that will be covered, with descriptions of why they are relevant.

Organizers and Speakers

  • Organizers’ names, titles, and affiliations and brief CVs
  • Names and affiliation of invited speakers. For each speaker, please indicate if attendance is tentative or confirmed.


  • Preference for half-day or full-day events.
  • Estimated numbers of orals, posters, and invited talks, with a rough program outline. (if applicable)
  • Expected number of paper submissions (if planned)
  • Tentative program committee (for workshops).
  • Anticipated target audience and expected number of attendees.
  • Special space or logistic requirements, if any.
  • For workshops, also specify: (i) Paper submission deadline, (ii) Notification to authors, (iii) Camera-ready deadline.

All proposals should be submitted by filling up this Google Form on or before May 31, 2022: Submission Link

Important Dates

  • Workshop and Tutorial proposal due: May 31, 2022
  • Notification to the organizers: June 15, 2022

For any inquiries you may have regarding the workshops, please contact the Workshop Chairs.
veronica.romero@uv.es , mishra@iitj.ac.in

More info: http://icfhr2022.org/call-for-wt.php

5) Call for Competitions ICFHR 2022

The ICFHR2022 organizing committee invites proposals for competitions that aim at evaluating the performance of algorithms and methods related to the field of handwriting recognition. 

You are cordially invited to submit a proposal that should contain the following information:

  • A brief description of the competition, including what the particular task under evaluation is and why this competition is of interest to the ICFHR community.
  • A draft of the outline of the competition describing the competition schedule, the expected number of participants and its rationale, which data is planned to be used, how the submitted methods will be evaluated, and which performance evaluation measures will be used.
  • The names, contact information, and brief CVs of the competition organizers, outlining previous experience in performance evaluation and/or organizing competitions.
  • The competition may be related to (but not limited to) the following areas:
    • Few-shot/zero-shot handwritten manuscript layout analysis/text recognition
    • Open set/open-world handwritten manuscript layout analysis/text recognition
    • Multilingual handwritten manuscript layout analysis/text recognition
    • Small size models for handwritten manuscript layout analysis/text recognition
    • Domain adaptation from printed to handwritten manuscript transcription
    • Transfer learning in handwritten manuscripts from one language to another
    • Degraded/low-quality handwritten manuscripts text recognition
    • Manuscript classification
    • Handwritten document image binarization
    • Historical scientific manuscript recognition
    • Image retrieval and text spotting for historical handwritten manuscripts
    • Detection, recognition and/or spotting of handwritten mathematical formula
    • Handwriting style analysis
    • Multi-script writer identification and retrieval
    • Online signature recognition and verification

The following rules shall apply to the accepted competitions:

  • Name of the competition must be standardized by starting with “ICFHR2022” (e.g. “ICFHR2022 Competition on …” or “ICFHR2022 … Competition.”).
  • Datasets used in the competitions must be made available through the TC10/TC11, online resources website after the end of the competitions (or equivalent arrangement by approval of the competition chairs).
  • Evaluation methodologies and metrics used must be described in detail so that results can be replicated later.
  • Participants should be encouraged to share their algorithms and code using one of the open-source licenses.
  • Competitions must have a sufficient number of participants (about 5, depending on the originality of the topic) to be able to draw meaningful conclusions.
  • Reports (full papers) on each competition will be reviewed and, if accepted (the competition runs according to plan and is appropriately described), will be published in the ICFHR2022 conference proceedings.
  • Competition results will be announced during a dedicated session of the ICFHR2022 conference.
  • Each competition has to be presented with a poster at a prominent place at the conference venue, selected competitions will get the chance to be presented orally in the dedicated session mentioned above.
  • Based on the analysis of the received proposals, the competition chairs will first synchronize with the competition organizers, and then submit a proposal to the program committee, in order to finalize the organization of the competitions.

Submission Guidelines

All proposals should be submitted by electronic mail to the competition chairs (Rohit Saluja and Maroua Mehri) via: rohit.saluja@research.iiit.ac.in  maroua.mehri@gmail.com 

Important Dates

  • Proposal due: June 05, 2022
  • Acceptance notification: June 12, 2022
  • Suggested deadline for competition participants: July 17, 2022
  • Initial submission of competition reports deadline: September 18, 2022
  • Camera-ready papers due: September 25, 2022


For any inquiries you may have regarding the competitions, please contact the ICFHR2022 competition Chairs (Rohit Saluja and Maroua Mehri) via: rohit.saluja@research.iiit.ac.in  maroua.mehri@gmail.com

More info: http://icfhr2022.org/call-for-com.php

6) Workshop on “Text in Everything” – ECCV 2022

Tel Aviv, Israel, October 2022
In conjunction with ECCV 2022

Understanding written communication through vision is a key aspect of human civilization and should also be an important capacity of intelligent agents aspiring to function in man-made environments. Interpreting written information in our environment is essential in order to perform most everyday tasks like making a purchase, using public transportation, finding a place in the city, getting an appointment, or checking whether a store is open or not, to mention just a few. As such, the analysis of written communication in images and videos has recently gained an increased interest, as well as significant progress in a variety of text based vision tasks. While in earlier years the main focus of this discipline was on OCR and the ability to read business documents, today this field contains various applications that require going beyond just text recognition, onto additionally reasoning over multiple modalities such as the structure and layout of documents.

Recent advances in this field have been a result of a multi-disciplinary perspective spanning not only computer vision, but also natural language processing, document and layout understanding, knowledge representation and reasoning, data mining, information retrieval, and more. The goal of this workshop is to raise awareness about the aforementioned topics in the broader computer vision community, and gather vision, NLP and other researchers together to drive a new wave of progress by cross pollinating more ideas between text/documents and non-vision related fields.

The workshop will be a hybrid, full-day event comprising invited talks, oral and poster presentations of submitted papers and a special challenge on Out of Vocabulary scene text understanding.

Keynote speakers

  • Xiang Bai (Huazhong University)
  • Tal Hassner (Meta AI)
  • Aishwarya Agrawal (University of Montreal, DeepMind)
  • Sharon Fogel (AWS AI Labs)

Topics of Interest

The workshop welcomes original work on any text-dependent computer vision application, such as:

  • Scene text understanding
  • Scene text VQA
  • Image-text aware cross-modal retrieval
  • Image-text for fine-grained classification
  • Text in video
  • Document VQA
  • Document layout prediction
  • Table detection
  • Information extraction

Challenge on Out-of-Vocabulary Scene Text Understanding

A challenge on Out of Vocabulary Scene Text Understanding (OOV-ST) will be organised in the context of this workshop. The OOV-ST challenge aims to evaluate the ability of text extraction models to deal with out-of-vocabulary (OOV) words, that have NEVER been encountered in the training set of the most common Scene Text understanding datasets to date. The challenge is organised jointly by Amazon Research, Google Research, Meta AI, and the Computer Vision Center.

To participate to the OOV_ST Challenge, please join through the RRC Portal.


Important dates

Paper Submission Deadline:         August 1, 2022

Notification to Authors:                 August 15, 2022

Workshop Camera Ready Due:   August 22, 2022

Workshop Date:                                October 2022


Ron Litman,                        AWS AI Labs

Aviad Aberdam,                AWS AI Labs

Shai Mazor,                         AWS AI Labs

Hadar Averbuch-Elor,     Cornell University

Dimosthenis Karatzas,    Computer Vision Center / Autonomous University of Barcelona

R. Manmatha,                    AWS AI Labs

7) Workshop on Identity Document Analysis and Verification – ICPR 2022

1st Workshop on Identity Document Analysis and Verification
Montréal (Québec), in conjunction with ICPR 2022.

WIDAV focuses on addressing theoretical and practical works related to the field of identity document analysis, both from static images and from videos. This workshop will be the opportunity to share the last advances in the field of ID document analysis among the community.  It will mainly include works from the fields of machine learning, document analysis, and forensics.

Topics of Interest:  

– Document localization in the wild  
– Identity document classification  
– Optical character recognition (OCR)  
– Fraud analysis and detection

Important dates :  

– Submission deadline                                   06 June 2022
 – Acceptance notification                             15 July 2022
 – Camera ready version                                 01 August 2022
 – WIDAV2022 Workshop                               TBD

Submission, attendance and publications:  

– WIDAV 2022 invites the submission of substantially original, previously unpublished work and also welcomes ICPR 2022 re-submissions.  
– Attendance and presentations for this first edition will be fully remote
– Accepted papers will be published by IEEE and be available in IEEE Xplore.

To find more information, please visit the workshop website: https://www.icpr-ariadnext.com/

8) Workshop on Reproducible Research in Pattern Recognition – ICPR 2022

Fourth Workshop on Reproducible Research in Pattern Recognition
Satellite event of ICPR 2022
21 Aug 2022 Montréal (Canada)

This Call for Papers expects two kinds of contributions.

The track 1 on RR Frameworks is dedicated to the general topics of Reproducible Research in experimental Computer Science with clear links to Image Processing and Pattern Recognition. Papers describing experiences, frameworks or platforms are welcome. The contributions might also include discussions on software libraries, experiences highlighting how the works benefit from Reproducible Research.

In the track 2 on RR Results, authors are invited to describe their works in terms of Reproducible Research. For example, authors of papers already accepted to ICPR might propose a companion paper describing the quality of the reproducible aspects. In particular the papers of this track can focus mainly (but not limited) for instance on:

  • Algorithmic implementation details
  • Influence of parameter(s) for the result quality (criteria to optimize them).
  • Integration of source code in an other framework.
  • Known limitations (or difficult cases).
  • Future improvements.
  • Installation procedure.

For this track, the topics could overlap with the main topics of the ICPR tracks:

  • Geometry and Deep Learning (special track)
  • Discrete Geometry and Mathematical Morphology
  • Pattern Recognition and Machine Learning
  • Computer Vision and Robot Vision
  • Image, Speech, Signal, and Video Processing
  • Document Analysis, Biometrics, and Pattern Recognition Applications.
  • Biomedical Image Analysis and Applications

9) Call for paper Pattern Recognition Letters – special issue

Advances and New challenges in Document Analysis, processing and Recognition at the Dematerialization Age


Description of the issue

Document Analysis and Recognition (DAR) aims at the processing, extraction and recognition of information contained in documents and initially addressed to human comprehension. Almost all sectors (banks, public administrations, etc.) are living a digital transformation boosted by the current COVID pandemic emergency. Different technologies characterize this scenario: mobile devices, standard acquisition and processing tools, cloud computing, cybersecurity and privacy are just some examples. The document is now part of an integrated and extended system which not only considers it as a standalone element, but it is also linked to many different users and to other digital elements including other documents, metadata, digital contents, and database records.

This special issue is devoted to present and collect the most recent advances to process documents in the stand-alone modality as well as in an integrated and extended way.

Document indexing, Natural Language Processing, summarization and translation are crucial steps for digital document archiving and augmentation. Nevertheless, it is well known that digital document containing handwriting can convey very sensitive information about the writer: age, sex, emotion, identity and health status are just some examples. Under this light, the processing of these data is very relevant in many applications deserving specific investigation as well as privacy preserving.

Papers presenting reviews, alternative perspectives, new applications and methods in the field of DAR are welcome. Research contributions should have a significant advancement both in the state-of-the-art for document analysis as well as for machine learning and pattern recognition fields.

Topics of interest

Topics of interest to this special issue include, but are not limited to:

  • Document Layout Analysis evaluation, recognition, semantic information extraction and benchmarking
  • Camera-based document scanning, processing, segmentation, and recognition
  • Document Understanding and information extraction
  • Structured and unstructured documents processing
  • Natural language processing, information extraction and retrieval
  • Handwritten/printed document images, information extraction and retrieval
  • Document Indexing
  • Handwritten text recognition
  • Document typeface, script and writing analysis and recognition
  • Object detection and structure modeling: tables, forms, identification documents, drawn sketches, etc.
  • Biometrics: writer identification and signature verification
  • Soft biometrics and meta-data extraction and manipulation
  • Deep Learning vs Shallow Learning techniques in real and benchmarking scenarios
  • Real-time document analysis
  • Interoperability of systems (e.g. cross dataset evaluations, standards,etc.)
  • Document augmentation
  • Human-Document Interaction
  • Large digital archives


Submission period: 1-20 July-2022

Guest Editors

Dr. Donato Impedovo (ME) – University of Bari Aldo Moro (Italy)
Dr. Byron Leite Dantas Bezerra – University of Pernambuco (Brazil)
Dr. Alejandro H. Toselli – Northeastern University (USA)
Dr. Giuseppe Pirlo – University of Bari Aldo Moro (Italy)

10) IJDAR article alert (vol. 25, issue 1)

Volume 25, Issue 1, March 2022

TableSegNet: a fully convolutional network for table detection and segmentation in document images
Duc-Dung Nguyen
TG2: text-guided transformer GAN for restoring document readability and perceived quality
Oldřich Kodym, Michal Hradiš
MRZ code extraction from visa and passport documents using convolutional neural networks
Yichuan Liu, Hailey James, Otkrist Gupta, Dan Raviv
An end-to-end network for irregular printed Mongolian recognition
ShaoDong Cui, YiLa Su, Ren Qing dao er ji, YaTu Ji
A novel normal to tangent line (NTL) algorithm for scale invariant feature extraction for Urdu OCR
Asma Naseer, Sarmad Hussain, Kashif Zafar, Ayesha Khan

11) IAPR Newsletter summary – April 2022

The April 2022 Issue of the IAPR Newsletter is available at: https://iapr.org/docs/newsletter-2022-02.pdf

In this issue you will find:

• From the Editor’s Desk: Add your voice to theirs, Gender Visibility in the Pattern Recognition Community, a collection of Her Stories
• Calls from the IAPR Education Committee, Industrial Liaison Committee, and ExCo
• IAPR…The Next Generation: Vishal M. Patel, winner of the 2021 Young Biometrics Investigator Award at IJCB 2021
• From the ExCo: News plus Gender Visibility in the Pattern Recognition Community, Part 2
• In Memoriam: Sargur N. Srihari
• ICPR 2022 Registration, Workshops, and Challenges
• IAPR Technical Committee (TC) News: TC1, TC4, TC5, TC6, TC7, TC12, TC18 and TC19
• Meeting Reports: CIARP Porto, ACPR 2021,
DICTA 2021, CVIP 2021, WSB 2022, and ISPR 2022
• Bulletin Board: Pattern Recognition Letters Special Issues
• Meeting and Education Planner

Wishing you all happy reading!

Stay safe,
Jing Dong
IAPR Newsletter Editor
Associate Professor, National Laboratory of Pattern Recognition
Institute of Automation, Chinese Academy of Sciences, Beijing, China

12) Job offers – 1 new

Research Engineer/PostDoc Position (2.5 Years) – IRISA/INSA Rennes (France) – new

Syntactical Models for Historical Music Score Recognition

PDF version: https://www.irisa.fr/offres-emploi/2022-03/syntactical-models-historical-music-score-recognition

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 researches 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, …).

Collabscore project

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 18 months, starting as soon a possible
  • Indicative salary: Up to €36 000 gross annual salary (according to experience), with social security benefits
  • Location: IRISA — Rennes, France


The engineer fellow will work on the conception of an 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 self-adaptative OMR system for historical orchestra scores. The tasks are mainly:

  • define a grammatical description of musical notation, using the existing DMOS-PI method;
  • integrate symbol recognizers developed in another part of the project;
  • integrate anomaly detection into the system.

Logical programming from grammars and languages is expected in this work.

Applicant Requirements

Master degree or PhD in computer science.
Experience in document recognition or statistical analysis is expected but not mandatory.
Skills in grammars and languages and/or logical programming are nice-to-have, as well as knowledge of music notation.

Candidates should contact via email: Bertrand Coüasnon (bertrand.couasnon@irisa.fr), Aurélie Lemaitre (aurelie.lemaitre@irisa.fr) and Yann Soullard (yann.soullard@irisa.fr).

Post-doctoral research position – L3i – La Rochelle, France

Title: Extraction of information in “Bande Dessinée” / Manga / Comics albums

The L3i laboratory has one open post-doc position in computer science, in the specific field of document image analysis and pattern recognition.

Duration: 24 months
Position available from: October 1st, 2021
Salary: approximately 2100 € / month (net)
Place: L3i lab, University of La Rochelle, France
Specialty: Computer Science/Image Processing/Document Analysis/Pattern Recognition/Deep Learning
Contact: Jean-Christophe BURIE (jcburie [at] univ-lr.fr)

Position Description

The L3i is a research lab of the University of La Rochelle. La Rochelle is a city in the south west of France on the Atlantic coast and is one of the most attractive and dynamic cities in France. The L3i works since several years on document analysis and has developed a well-known expertise in ‘Bande dessinée”, manga and comics analysis, indexing and understanding.

The work done by the post-doc will be part of the SAIL (Sequential Art Image Laboratory) a joint laboratory involving L3i and a private company. The objective is to create innovative tools to index and interact with digital comics. The work will be done in a team of 10 researchers and engineers.

The work entrusted to the recruited person will consist in developing original approaches for extracting relevant information in comics panels in order to understand its content. The team has already developed some methods to extract panels, speech balloons, text, characters (persons), faces. However, the large variability of representation of these elements requires to propose different approaches or strategies. According to the skills and knowledge of the candidate, he/she will be able to work to improve methods dedicated to one of these elements.

Other challenges may also be considered such as :

  • Detection and understanding of the scenery (sea, countryside, city, …)
  • Detection and understanding of the context of the scene (battle, discussion, people eating, …)
  • Object detection and recognition (bicycle, car, table, chair, …)

Traditional and/or deep learning-based strategies can be studied to achieve these objectives.


Candidates must have a completed PhD and a research experience in image processing and analysis, pattern recognition. Good knowledge and experience in deep learning are also recommended.

General Qualifications

• Good programming skills mastering at least one programming language like Python, Java, C/C++
• Good teamwork skills
• Good writing skills and proficiency in written and spoken English or French


Candidates should send a CV and a motivation letter to jcburie [at] univ-lr.fr.