============================================================================ IAPR TC-11 Newsletter January 2013 http://www.iapr-tc11.org ========== Contents ======================================================== * Message from the Editor * Dates 'n' Deadlines - ICDAR 2013, Washington, USA February 15 (extended!) * New and Recently Published Datasets * ICDAR 2013 Final Call for Papers and Deadline Extension * Announcements: - Doctoral Consortium at ICDAR 2013 - ICDAR 2013 Competition on Historical Book Recognition (HBR2013) - ICDAR 2013 Competition on Historical Newspaper Layout Analysis (HNLA2013) * Call for Nominations: ICDAR 2013 Awards * Calls for Papers: - ACM Symposium on Document Engineering (DocEng 2013), September 10-13 2013, Florence, Italy - Int. Workshop on Historical Document Imaging and Recognition (HIP'13), August 24, 2013, in conjunction with ICDAR 2013 * Call for Participation: - MAURDOR 2013 Evaluation Campaign for scanned document processing * Job Opportunity: - Post-doctoral position at the University of Nantes, France (repost) * Call for Dataset Submissions * Call for Contributions ============================================================================ ========== Message from the Editor ========================================= Welcome to the first edition of our TC11 newsletter in 2013 which brings good news to prospective ICDAR authors: The paper submission deadline for ICDAR 2013 has been extended! Please note, however, that all submissions have to be registered with the ICDAR submission system by the original deadline. For details see the Final Call for Papers below. This edition also brings to you the announcement of the Doctoral Consortium which will be jointly organized by IAPR TC-10 and TC-11 in conjunction with ICDAR. As in previous years ICDAR will also feature a couple of competitions. The announcements of the Historical Book Recognition Competition (HBR2013) and the Historical Newspaper Layout Analysis Competition (HNLA2013) you will find below. Furthermore, this newsletter brings to you the Call for Nominations for this year's ICDAR awards which are the IAPR/ICDAR Young Investigator Award and the IAPR/ICDAR Outstanding Achievements Award. Finally, this newsletter also includes the Calls for Papers for DocEng 2013 (Florence, Italy) and HIP 2013 (in conjunction with ICDAR) as well as the Call for Participation for the MAURDOR 2013 Evaluation Campaign. Gernot A. Fink, IAPR-TC11 Newsletter Editor Gernot.Fink@udo.edu ============================================================================ ========== Dates 'n' Deadlines ============================================= Event/Location/Web: Event Date: Deadline (paper submission): ---------------------------------------------------------------------------- * ICDAR 2013, Washington, USA August 25-28 (February 1) (http://www.icdar2013.org/) February 15 - Doctoral Consortium: August 25 May 25 * DocEng 2013, Florence, Italy September 10-13 March 31 (http://www.doceng2013.org) (April 7) * HIP'13 in conjunction with ICDAR'13 August 24 May 15 (http://www.cvc.uab.es/~vfrinken/HIP2013) * ACPR 2013, Okinawa, Japan November 5-8 June 10 (http://www.am.sanken.osaka-u.ac.jp/ACPR2013/) ============================================================================ ========== New and Recently Published: TC-11 Datasets ====================== Name/Source of Dataset: Main Purpose: Published: ---------------------------------------------------------------------------- * MSRA 500 Database Text Detection 11/2012 http://www.iapr-tc11.org/mediawiki/index.php/MSRA_Text_Detection_500_Database_(MSRA-TD500) * CROHME Recognition of Online 11/2012 HW Math Expressions http://www.iapr-tc11.org/mediawiki/index.php/CROHME:_Competition_on_Recognition_of_Online_Handwritten_Mathematical_Expressions For a list of all datasets available visit: http://www.iapr-tc11.org/mediawiki/index.php/Datasets_List ============================================================================ ========== ICDAR 2013 Final Call for Papers and Deadline Extension ========= <<<<< new deadline : February 15th, 2013; 24:00 PST >>>>> Authors should input the title and abstract of their paper on the submission site by February 1st, 2013; 24:00 PST. ======================================================================= 12th International Conference on Document Analysis and Recognition (ICDAR 2013) August 25-28, 2013 Conference web site: http://www.icdar2013.org/ ======================================================================= We are pleased to issue this call for papers for the Twelfth International Conference on Document Analysis and Recognition (ICDAR 2013), sponsored by the International Association for Pattern Recognition (IAPR) TC-10 (Graphics Recognition) and TC-11 (Reading Systems). ICDAR is the premier international forum for researchers and practitioners in the document analysis community for identifying, encouraging and exchanging ideas on the state-of-the-art technology in document analysis, understanding, retrieval, and performance evaluation. The term document in the context of ICDAR encompasses a broad range of documents from historical forms such as palm leaves and papyrus to traditional documents and modern multimedia documents. The topics of interest include, but are not limited to: Character Recognition Handwriting Recognition Graphics Recognition Document Image Analysis Document Understanding Document Analysis Systems Camera-based Document Processing Basic Research and Methodologies for Document Processing Document Databases and Digital Libraries Multimedia Documents Forensic Documents Historical Documents Novel Applications Sketching Interfaces Performance Evaluation -------------------- Conference Outline: -------------------- The conference will be held at the Omni Shoreham hotel in Washington DC, USA with the main conference being held 25th-28th August 2013, workshops on the 23rd and 24th, and half-day tutorials on the 24th and 25th. A doctoral consortium will be held on the afternoon of the 25th. Manuscripts of a maximum length of five pages are encouraged to be submitted. Papers must describe original work on any of the ICDAR related topics. The format templates and instructions for paper submission is available on the Conference web site. The deadline for paper submission is 24:00 PST, February 15, 2013. The review process will include a rebuttal opportunity for authors. Our goal is to provide a transparent and fair review process ensuring a high quality technical program. Calls for satellite Workshops, Tutorials, Competitions and Sponsorships are now available on the Conference Web site. ----------------- Important dates ----------------- Paper Submission: Feb 15, 2013; 24:00 PST Acceptance Notification: May 1, 2013 Camera Ready Papers Due: Jun 1, 2013 Advanced Registration: Jun 1, 2013 Main Conference: Aug 25-28, 2013 Workshops: Aug 23-24, 2013 Tutorials: Aug 24-25, 2013 Doctoral Consortium: Aug 25, 2013 ----------- Organizing Committee ----------- Honorary Chair: George Nagy, RPI, USA General Chair: David Doermann, University of Maryland, USA General Co-Chairs: Venu Govindaraju, University at Buffalo, USA Daniel Lopresti, Lehigh University, USA Prem Natarajan, Raytheon BBN Technologies, USA Program Committee Chairs: Elisa Barney Smith, Boise State University, USA Abdel Belaid, LORIA, France Koichi Kise, Osaka Prefecture University, Japan Workshop Chair: Apostolos Antonacopoulos, University of Salford, UK Tutorial Chair: Simone Marinai, University of Florence, Italy Competitions Chairs: Volker Märgner, Technische Universität Braunschweig, Germany Haikal El Abed, Technische Universität Braunschweig, Germany Publications Chair: Srirangaraj(Ranga)Setlur, University at Buffalo, USA Sponsorship Chair: Andreas Dengel, Technische Universität Kaiserslautern, DFKI, Germany Publicity Chairs: Wael Abd-Almageed, University of Maryland, USA Srirangaraj(Ranga)Setlur, University at Buffalo, USA Finance Chair: Rohit Prasad, Raytheon BBN Technologies, USA Doctoral Consortium Chair: Marcus Liwicki, Technische Universität Kaiserslautern, DFKI, Germany Secretariat: David Frampton & Laura Stephens, Raytheon BBN Technologies, USA Eugenia Smith & Ed Sobczak, University at Buffalo, USA ============================================================================ ========== Doctoral Consortium at ICDAR 2013 =============================== After the great success at ICDAR 2011, the leadership of IAPR TC-10/TC-11 plans to continue organizing a Doctoral Consortium in conjunction with ICDAR 2013. It will be jointly organized by Marcus Liwicki and Josep Llados. More information below. If you are willing to participate as a student or if you are able to mentor a PhD-student, please tick one of the options in the following poll (This poll is not the definite registration yet, but it helps us in the organization): doodle.com/m25zywknn9epvr6k The goal of the Doctoral Consortium is to create an opportunity for Ph.D. students to test their research ideas, present their current progress and future plans, and receive constructive criticism and insights related to their future work and career perspectives. A mentor (a senior researcher who is active in the field) will be assigned to each student to provide individual feedback. In addition, students will have the opportunity to present an overview of their research plan during a special poster session. Participation in the IAPR TC-10/11 Doctoral Consortium will be by invitation only and will be limited to 25 students. Students willing to participate will submit their application around May (deadline and submission information will be announced in February). Preference will be given to students who are at a stage in their studies most likely to benefit (i.e., they have identified a research direction and published some initial results, but the thesis is not yet "cast in stone"). The event will be designed so that the extra expense is minimal for all involved. The Doctoral Consortium will take place the day before ICDAR (August 25). The tentative important dates are: Submission deadline: May 25 Acceptance notification and Mentor assignment: June 10 Final material due: July 25 Doctoral Consortium: August 25 We are looking forward to your participation! Marcus Liwicki & Josep Llados ICDAR 2013 Doctoral Consortium Organization Team ============================================================================ ========== Announcement: ICDAR 2013 Competitions ========================== ICDAR2013 Competition on Historical Book Recognition (HBR2013) Historical books represent a large proportion of libraries' holdings and continue to be the focus of large-scale digitisation projects. A number of distortions frequently manifest themselves in scans of historical books, hindering layout analysis and text recognition. The motivation of the competition is to evaluate existing approaches using a truly representative dataset and an objective performance analysis system. Participating systems will be evaluated in different stages (e.g. segmentation, classification, recognition) according to how far their methods are applicable within the analysis and recognition workflow - not all participating systems have to be end-to-end applications. Register now: http://www.primaresearch.org/HBR2013 ICDAR2013 Competition on Historical Newspaper Layout Analysis (HNLA2013) Historical newspapers pose a series of challenges due to the method of their production (inexpensive paper, inconsistent inking, varying layout etc.) as well as the presence of ageing and use artefacts. Newspapers are increasingly the major focus of large-scale digitisation projects (e.g. Europeana Newspapers) as they contain information that is widely interesting to the general public and, at the same time, are rapidly deteriorating in storage. The motivation of the competition is to evaluate existing approaches using a realistic dataset (reflecting a subset of current digitisation projects) and an objective performance analysis system. Register now: www.primaresearch.org/HNLA2013 ============================================================================ ========== Call for Nominations: ICDAR 2013 Awards ======================== ======================================================================== INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR) CALL FOR NOMINATIONS FOR ICDAR 2013 AWARDS Nominations Due: May 15, 2013 ======================================================================== The 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: o Research o Training of students o Research/Industry interaction o Service to the profession Every two years, two awards 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 will consist of a token gift and a suitably inscribed certificate. The recipient of the Outstanding Achievements award will be invited to give the opening key note speech at the ICDAR 2013 conference, introduced by the recipient from the previous conference. Nominations are invited for the ICDAR 2013 Awards in both categories. The nomination packet should include the following: 1. A nominating letter (1 page) including a brief citation to be included in the certificate. 2. A brief vitae (2 pages) of the nominee highlighting the accomplishments being recognized. 3. Supporting letters (1 page each) from 3 active researchers from at least 3 different countries. A nomination is usually put forward by a researcher (preferably from a different Institution than the nominee) who is knowledgeable of the scientific achievements of the nominee, and who organizes letters of support. Submission procedure is strictly confidential, and self nominations are not allowed. The final decision will be made by the Awards Committee which is composed of the following members : Daniel Lopresti, USA (Co-Chair) Jean-Marc Ogier, France (Co-Chair) Dave Doermann, USA Masakazu Iwamura, Japan Koichi Kise, Japan Cheng-Lin Liu, China Josep Llados, Spain Umapada Pal, India Sargur Srihari, USA Karl Tombre, France ============================================================================ ========== Call for Papers: DocEng 2013 =================================== CALL FOR PAPERS Join us in Florence for the 13th ACM Symposium on Document Engineering (DocEng 2013), September 10-13 2013, at the University of Florence, Italy http://www.doceng2013.org ----------------------------------------------------------------------- Documents are communication artifacts in any form and in any media; they can be simple or compound, static or time-varying, private or open. Document collections increasingly underpin research, education, commerce, entertainment - the full range of human activity. Document engineering covers both the innovative use of documents and document collections in real-world applications and the study of principles, tools and processes that improve our ability to create, manage, maintain, share, and productively use these. You are invited to submit original papers to the 13th ACM Symposium on Document Engineering (DocEng 2013), to be held at the University of Florence. Attendees at this international forum have interests that span all aspects of document engineering and applications. DocEng is sponsored by ACM by means of the ACM SIGWEB Special Interest Group. Proceedings are available through the ACM Digital Library. Important dates: ================ * Mar 15, 2013: Workshop and tutorial proposals due * Mar 31, 2013: Full paper abstracts due * Apr 7, 2013: Full papers due * May 19, 2013: Short paper abstracts due * May 22, 2013: Short papers due Topics relevant to the symposium include (but are not limited to): ================================================================== Modeling and Representation: * Document representation and standards including interchange standards, markup languages (incl. SGML), stylesheets, type representation, multimedia (incl. HTML5, MPEG, SMIL, SVG), eBook standards (ePub) * Metadata creation and standards, use of semantic web technologies * Hypertext/hypermedia, distributed documents, blogs, wikis * Linking techniques and standards, integration with other digital artifacts Generation, Manipulation, and Presentation: * Document authoring tools and systems * Document presentation (typography, formatting, layout) algorithms and systems (TeX, browsers) * Automatically generated documents, automated layout and composition, variable data printing * Adaptive, responsive documents, content customization * Mobile platforms and documents * Document transformation and rich-web-client models Collections, Systems, and Management: * Collections databases and repositories, storage, indexing, retrieval, versioning, deduplication * Enterprise content management: models and standards (CMIS), scale and performance, platforms and applications * Digital libraries and archives, preservation systems * Document system components: security, APIs (SAX, DOM), versioning, synchronization * Document systems and workflows Document Analysis: * Structure and representation analysis (layout, OCR, visual analysis) * Linguistic and semantic (content) analysis, categorization, classification Internationalization: * Document internationalization, multilingual representations * Multi-lingual and cross-lingual indexing and search User Experience: * Navigation, search * Usability, accessibility, readability and aesthetics * Collaborative authoring and editing, curation and annotation * Workflows, integration and interaction between human and automated processes Applications: * Digital humanities, digital preservation and archiving * eBooks and digital publishing ... and all other application areas For more information, please visit the conference website at: http://www.doceng2013.org ============================================================================ ========== Call for Papers: HIP 2013 ====================================== CALL FOR PAPERS 2nd International Workshop on Historical Document Imaging and Recognition (HIP'13) which will be held August 24, 2013 in conjunction with ICDAR 2013 at the Washington DC Omni Shoreham hotel in Washington, DC, USA http://www.cvc.uab.es/~vfrinken/HIP2013 Recent years have seen an increased effort to scan, index, and provide access to historical documents held in archives and special collections that are often inaccessible to the world in general. ICDAR 2009 featured both a half day tutorial and single technical paper session dedicated to historical document processing. Two years later at ICDAR 2011, the first workshop dedicated entirely on this topic was a great success with overwhelming participation. This year, a one-day workshop continues the effort to bring together researchers working with historical documents and is intended to be complementary and synergistic to the work in analysis and recognition featured in the main ICDAR sessions. Workshop topics include (but are not limited too): Imaging and Image Acquisition - Imaging for fragile materials - Multispectral imaging - Camera-based/non-invasive acquisition - Case studies/applications Digital Archiving Considerations - Compression issues - Measuring essential resolution (color, spatial) and metadata - Modeling 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, supporting documents, i.e. inpainting, etc. - Machine-learning algorithms for enhancement based on example images - Interactive tools from a user viewpoint - Learning from user-directed image enhancement Content Extraction (within the context of historical documents) - Content-based retrieval - Automated or semi-automated transcription - Content recognition based on surrounding and supporting context - Ontologies for modeling 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 (typography of printed text, handwriting style recognition for manuscript authentication or author identification...) - Searching for Documents over the Internet - On-line and web-based navigation within/among document images - Searching/querying, retrieval, summarizing/condensing of document images - Collecting, linking, analysis and search technologies - Parallel tagging of images, transcripts, and other document layers Important Dates: May 15, 2013: Paper submission June 30, 2013: Decision notification. July 15, 2013: Final paper submission. July 15, 2013: Early registration deadline. ============================================================================ ========== Call for Participation: MAURDOR 2013 Evaluation Campaign ======= MAURDOR-campaigns: Scanned documents processing evaluations ** Presentation ** Scanned documents processing is an important issue for information retrieval. The MAURDOR campaigns aim at assessing the progress of the automatic systems in this area. The goal is to quantify and qualify the ability of the systems to extract the relevant information in scanned documents. The Laboratoire national de métrologie et d'essais (LNE) and CASSIDIAN, an EADS company, will conduct evaluation campaigns entitled MAURDOR in 2013 in order to support Scanned documents processing researches and help advance the state of the art in Optical Characters Recognition technologies. The LNE and CASSIDIAN provide the following to the participants: - Consistent data for the training sets, the development and the test sets. - Automatic metrics tools. - Common rules so as to assess the different steps essential for scanned documents processing. A workshop will be organized at the end of the campaign to account for the results and compare the approaches of various participants. The evaluation plan is available at www.maurdor-campaign.org ** A heterogeneous database ** The MAURDOR evaluations are based on a very heterogeneous database. The training set is multilingual (English, French, and Arabic) and consists on 5,000 different documents corresponding to the following classes: - Blank forms and completed forms (around 12% of the database) - Typewritten commercial documents with sometimes several manual annotations (around 40% of the database) - Handwritten personal letters with sometimes typewritten headers (around 25% of the database) - Commercial letters (around 20% of the database) as purchase orders or bills - Other documents like newspapers articles or maps (around 3% of the database). The test set contains 1,000 documents distributed as the training set. ** Tasks ** MAURDOR is based on a complete processing in which five separate modules are implemented. Each module performs a particular function contributing to the complete processing of the scanned document. The following five modules are independently assessed during the campaign: - Task 1: Segmentation and typing areas (table, text, image) - Task 2: Type writing characterization (handwritten or typewritten characters) - Task 3: Language detection - Task 4: Characters recognition - Task 5: Establishing reading order and relations between areas An evaluation will be performed for an operational application as an end-to-end processing chain. It will consist in the assessment of the completion and the accuracy of the results according to the presence of keywords in the recognized text. ** How to participate? ** This evaluation is intended to be of interest of all researchers working on the problem of scanned documents processing. Participation in the evaluation is invited for all researchers who find the tasks and the evaluation of interest. The only requirement is the participation in the follow-up workshop. All the participants must attend the evaluation workshop and be prepared to discuss their system(s), their results in detail. To participate, simply fill out the registration form available at www.maurdor-campaign.org ** Important dates ** Evaluation plan released 01/12/2012 Training data available 01/12/2012 Beginning of the campaign 04/03/2013 End of the campaign 29/04/2013 Beginning of the adjudication 29/04/2013 End of the adjudication 06/05/2013 Workshop May 2013 Another campaign will be organized in 2014. ============================================================================ ========== Job Opportunity: Post-doct at University of Nantes (repost) ===== *"From segmentation to description and grammatical analysis for interpretation of handwritten and audio structured documents"* This work, which is part of the DEPART project funded by the Regional council of Pays de la Loire, is focused on the interpretation of mathematical expressions (ME) from online handwritten and audio sources. The problem of a correct segmentation and of subsequent graph based descriptions relying on a specific grammar which controls the language domain is of prime importance. We are interested in extending the formalism used currently to control 1D (one dimensional) segmentation to deal with 2D languages + audio stream. In the case of linear textual languages it is clear how to replace a non-terminal in a sentence by a corresponding sequence of (non-)terminals. But in the case of graphical languages, with many possible relationships between language elements, we need a far more complicated mechanism for (re-)establishing relationships between the surrounding of a replaced non- terminal and its replacing (non-)terminals. In addition, the information extracted from the audio source should be integrated in the global framework. We will study different strategies to cope with this problem. They will include CFG approaches as well as Context Dependant Grammar (CDG). Specifically, graph grammars will be considered and their potential interest to describe graphical languages such as Mathematical Expressions. The design of an efficient parsing algorithm will also be part of this work. The results of this work will be transferred into our existing ME recognition platform and will participate to the forthcoming competitions. In addition, the improvement of the grammar based modeling will allow to address other interesting structured documents. Location of the post-doct : Ecole polytechnique de l'Université de Nantes http://web.polytech.univ-nantes.fr/ in the IVC lab : http://www.irccyn.ec-nantes.fr/IVC Duration: 12 months Period : from 01/01/2013 Qualifications and skills required: · PhD related to Pattern recognition. · Good mathematical understanding. · High motivation for research. · Capability of working in an autonomous way. · Good programming skills in either C, C++, Python. · Good communication skills in English, both in written and oral form. Applicants should submit: 1) Application letter 2) Curriculum Vitae and Academic Record 3) Letters of Reference (if available) Contact: send application form with letters of recommendation to Christian.viard-gaudin@univ-nantes.fr ============================================================================ ========== Call for Dataset Submissions ==================================== We would like to remind you that the TC10 and TC11 welcome contributions of new datasets or other resources related to the community. We would like to particularly encourage authors of articles that introduce new datasets, software or other material to submit such material to TC11 for hosting. Please check the TC11 site on information about how to submit datasets for archiving ( http://www.iapr-tc11.org/mediawiki/index.php/Datasets) also feel free to contact Dimosthenis Karatzas, the TC11 dataset curator, for any doubts you might have on the process. Dimosthenis Karatzas, TC-11 Dataset Curator dimos@cvc.uab.es ============================================================================ ========== Call for Contributions ========================================== This newsletter needs your support in order to provide useful information to the TC11 community. Therefore, please contribute relevant news by sending a short notice to the newsletter editor Gernot A. Fink . Such news could be the obvious announcements of conferences and workshops, job opportunities, reports on past conferences, book reviews, or anything that might be of interest to a wider audience involved in the construction of reading systems. ============================================================================ ========== Subscription Information ======================================== This newsletter is sent to subscribers of the IAPR TC11 mailing list. To manage your subscription, please visit the mailing list homepage at: https://www.jiscmail.ac.uk/cgi-bin/webadmin?A0=IAPR-TC11 The homepage for IAPR TC11 is http://www.iapr-tc11.org ============================================================================