The Tenth International Workshop on Graphics Recognition (GREC 2013), organized by the IAPR TC-10, took place at Lehigh University, Bethlehem, PA, USA on August 20-21, 2013, just before ICDAR 2013, Washington, D.C., USA.
Once again, the GREC workshops prooved to be an excellent opportunity for researchers and practitioners at all levels of experience to meet and to share new ideas and knowledge about graphics recognition methods. The level of interaction was intense and rich as usual.
This year, 29 participants registerd for the workshop, 4 of which, unfortunately encountered visa delays and could not attend. Represented countries were Brazil, China, France, Germany, India, Japan, Luxemburg, Malaysia, Spain, Switzerland and the USA.
Full access to presented papers is available from the Program page (http://grec2013.loria.fr/GREC2013/node/13), but is restricted to attendees only. A selection of fully reviewed papers will be published by Springer as an LNCS volume in 2014.
Post-conference proceedings in LNCS
Selected papers will be published in post-conference proceedings in the Springer Lecture Notes in Computer Science series.
- November 30, 2013 : extension, revision, and re-submission - February 28, 2014 : 2nd round revision again based on the review comments - April 2013 : camera-ready version sent to LNCS - June-July 2013 : Publication by LNCS. Copies sent to individual registered participant
After the successful first Summer School on Document Image Processing (IDIPS2013), (http://www.iapr.org/docs/newsletter-2013-03.pdf p.13-14) the second Summer School on Document Image Processing (IDIPS2014) aims to provide both an objective overview and an in-depth analysis of the state-of-the-art of the Document Analysis Systems (DAS) and their current open issues. The courses will be delivered by world-renowned researchers in the field and relevant companies, covering both theoretical and practical aspects of real problems of Document Analysis Systems, as well as examples of successful applications. This year, the school aims to provide an attractive opportunity for 40 young researchers, post-graduate and PhD students. The participants will benefit from direct interaction and discussions with the renowned speakers and practice on real problems.
Program Chairs - Apostolos Antonacopoulos, PRImA, University of Salford - Ergina Kavallieratou, University of the Aegean - Josep Llados, CVC, University Autonoma de Barcelona
Program Committee - David Doermann, University of Maryland - Daniel Lopresti, Lehigh University - Jean-Marc Ogier, Universite de La Rochelle - Ioannis Pratikakis, Democritus University of Thrace
Important Dates - APPLICATION: 1/1/14 - 30/4/14 (or up to 40 persons) - Acceptance Notification: 10 days after the application - Local Arrangements Information available by: 15 May 2014 - Summer School: 26-30 May 2014
ImageCLEF 2014: Call for participation
ImageCLEF 2014 is part of the CLEF 2014 Labs and will organize the following four main tasks: Robot Vision, Scalable Concept Image Annotation, Liver CT Annotation, Domain Adaptation.
These tasks will benchmark the challenging task of image annotation for a wide range of source images and annotation objective, such as general multi-domain images for object or concept detection, as well as domain-specific tasks such as visual-depth images for robot vision and volumetric medical images for automated structured reporting.
The tasks address different aspects of the annotation problem and are aimed at supporting and promoting the cutting-edge research addressing the key challenges in the field, such as multi-modal image annotation, domain adaptation and ontology driven image annotation. The lab is envisioned to serve as a benchmark for the aforementioned research fields.
The registration system for ImageCLEF 2014 is now up and running, so you can start registering for the tasks now. All information about registration procedure, end user agreement and how to transfer your account from a previous year can be found at:
International Conference on Pattern Recognition Applications and Methods (ICPRAM) Angers, Loire Valley, France March 6 - 8, 2014 http://www.icpram.org/
The International Conference on Pattern Recognition Applications and Methods would like to become a major point of contact between researchers, engineers and practitioners on the areas of Pattern Recognition, both from theoretical and application perspectives.
Contributions describing applications of Pattern Recognition techniques to real-world problems, interdisciplinary research, experimental and/or theoretical studies yielding new insights that advance Pattern Recognition methods are especially encouraged.
CONFERENCE AREAS 1 . Theory and Methods 2 . Applications
Position Paper: a short report of work in progress or an arguable opinion about an issue discussing ideas, facts, situations, methods, procedures or results of scientific research focused on one of the conference topic areas.
IMPORTANT DATES Position Paper Submission: November 19, 2013 (EXTENDED DEADLINE) Authors Notification (position papers): December 23, 2013 Final Position Paper Submission and Registration: January 8, 2014
The DATeCH international conference brings together researchers and practitioners looking for innovative approaches for the creation, transformation and exploitation of historical documents in digital form.
The workshop aims to foster interdisciplinary work and linking together participants engaged in the following areas:
Text digitization and OCR. Digital humanities. Image and document analysis. Digital libraries and library science. Applied computational linguistics. Crowdsourcing. Interfaces and human-computer interaction.
Topics of interest are all those related to the practical and scientific goals listed above, such as:
OCR technology and tools for minority and historical languages. Methods and tools for post-correction of OCR results. Automated quality control for mass OCR data. Innovative access methods for historical texts and corpora. Natural language processing of ancient languages (Latin, Greek). Visualization techniques and interfaces for search and research in digital humanities. Publication and retrieval on e-books and mobile devices. Crowdsourcing techniques for collecting and annotating data in digital humanities. Enrichment of and metadata production for historical texts and corpora. Data created with mobile devices. Data presentation and exploration on mobile devices. Ontological and linked data based contextualization of digitized and born digital scholarly data resources.
IMPORTANT DATES Paper submission deadline: 7 January 2014 Decision notification: 28 February 2014 Camera-ready papers due: 31 March 2014
The following criteria will be applied to all communications submitted to DATeCH 2014 (http://datech2014.info/submissions) : - Only original material will be accepted. - All communications will be peer reviewed and published in the proceedings of the conference. - The authors of the best contributions will be invited to prepare an extended version for a collective publication of selected papers in an indexed journal (an additional reviewing process will be applied).
In addition to the original contributions, we also invite authors to submit their recent papers (within 1 year) published in a related journal (e.g. PAMI, PR, PRL, JMLR). These papers will undergo a lighter review process, and if accepted, they will be included in the workshop program and short abstract in the proceedings.
PAPER SUBMISSION PROCEDURE
All manuscripts (max. 10 pages) must be in LaTex format following Springer's LNCS style:
All papers are submitted via EasyChair, and will be reviewed at least two or more anonymous reviewers. Accepted papers (not exceeding 10 pages) will be published in Springer's Lecture Notes in Computer Science (LNCS) series, providing that at least one author will register to the workshop and present the paper.
Scanned documents processing is an important issue for information retrieval. The MAURDOR campaigns aim at assessing the progress of automatic systems in this area. The goal is to evaluate the ability of the systems to extract relevant information in scanned documents. After the success of the first campaign that took place in spring 2013, the Laboratoire national de métrologie et d'essais (LNE) and CASSIDIAN, an EADS company, will conduct a new MAURDOR evaluation campaign in order to support research in Scanned documents processing and help advancing the state of the art in Optical Characters Recognition technologies.
The LNE and CASSIDIAN provide the following to participants: - Consistent data for training, development and test sets. - Automatic scoring tools. - Common rules needed to assess 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 of 7,000 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 such as purchase orders or bills (around 20% of the database) - Other documents like newspapers articles or maps...(around 3% of the database).
The test set contains 1,000 documents. The proportion of documents belonging to different categories is the same as for the training data.
MAURDOR is based on a complete processing chain in which five separate modules are implemented. Each module performs a particular function contributing to the complete processing of a 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 identification - Task 4 : Optical Characters Recognition - Task 5 : Establishing reading order and relations between areas
Participants can submit systems for individual tasks of their choice. An evaluation will also be performed for an operational application as an end-to-end processing chain. It is evaluated in a keyword spotting scenario.
How to participate?
This evaluation is intended to be of interest of all researchers working on the problem of scanned documents processing. The only requirement is the participation in the closing workshop. All the participants must attend the evaluation workshop and be prepared to discuss their system(s), their results in detail. To participate it is sufficient to fill out the registration form available at www.maurdor-campaign.org
IMPORTANT DATES - Evaluation plan released : 01/07/2013 - Training data available : 01/07/2013 - Beginning of the campaign : 04/11/2013 - End of the campaign : 02/01/2014 - Beginning of the adjudication : 02/01/2014 - End of the adjudication : 10/01/2014 - Workshop : February 2014
Call for papers
Deadline (paper submission)
ICPRAM 2014, Angers, France Int. Conf. on Pattern Recognition Applications and Methods, http://www.icpram.org/
S+SSPR 2014: Joensuu, Finland Statistical Techniques in Pattern Recognition Structural and Syntactic Pattern Recognition http://cs.uef.fi/ssspr2014/
20-22 August 2014
March 1, 2014
Call for datasets
We would like to remind you that the TC10 and TC11 Web sites always welcome contributions of new datasets or other resources related to the community. We would like to encourage all the TC10 and TC11 members to submit such material to the TC10 and TC11 for archiving. The availability of datasets, ground truth and performance evaluation tools online is not only good practice, but also a requirement for a field to progress.
We would like make a special request to the organizers of recent and future competitions. Independently of whether you have the competition datasets and evaluation tools available through other Web sites, please consider archiving them with TC10 / TC11 as well. Web sites often go off-line and useful resources are frequently lost forever.