On 7 May 2021 will be the inaugural session of our new barcamp-like monthly event OCR(-D) & Co. barcamp format, developers, users and all other interested persons will be will be given the opportunity to talk about OCR(-D).

The coordination project’s application for the third phase of the OCR-D funding initiative was approved by the DFG in January 2021. In phase III, we will optimise the results of the previous module project phase and we will initiate the productive use of the OCR-D software in mass digitisation both technically and organisationally.

On October 20, 2020 the Mini-ELAG (European Library Automation Group) takes place, where librarians and IT professionals discuss new information technologies and their application in libraries and documentation centers. OCR-D will be represented at virtual conference with a lecture by Clemens Neudecker (SBB) on OCR-D: An open ecosystem for improving OCR on historical documents.

From October 7 to 8, the eHumanities working group of the Union of German Academies of Sciences and Humanities, in cooperation with the Göttingen Academy of Sciences and Humanities, is organizing the workshop FAIR & Co: Visibility and Availability of Digital Academy Research in a Networked Scientific Landscape. The OCR-D project will be represented with a lecture on the topic Digital Transformation: OCR-D, Offer and Vision by Matthias Boenig (BBAW). Using the example of the German Text Archive, it will be shown how the application spectrum of this reference corpus can be extended by the area of machine learning to improve character and structure recognition. For the whole program of the workshop see the website of this workshop.

Following the successful first (virtual) meeting of those interested in the DFG-call for the implementation of the OCR-D-Software, a further workshop will be held on 7 August, 9-13 p.m. to prepare the OCR-D grant proposals.

We are very happy about the great interest in the DFG call for proposals for the implementation of the OCR-D software. As OCR-D coordination project we will support the planned projects from the pilot phase onwards and promote the exchange of information among interested parties as desired by the DFG. To kick off the pilot phase, we are organising a large video conference on 19 June, 9-13 o’clock, at which all interested parties can get to know each other and the pilot tests can be coordinated. Interested parties who have not submitted a letter of intent themselves and who are still looking for a suitable partner with whom they could engage in the third phase of OCR-D are also welcome to the video conference. If you are interested, please register for the video conference by 12 June at engl@hab.de. We look forward to working with you and to a successful pilot phase!

The call for the implementation of the OCR-D software for the full text digitisation of historical prints is now available on the website of the German Research Association (DFG).

The OCR-D funding initiative will be represented with several presentations at the DHd 2020, which will take place in Paderborn from 2-6 March. In V15, on March 5, the OCR-D coordination project will discuss the results and perspectives of the funding initiative on the basis of four theses on full text transformation. In the same section, the colleagues of the module project for the development of a model repository and automatic font recognition for OCR-D will report on their findings on the use of fracture in German-language books. For further information on the presentations see the DHd program.

The OCR-D workshop “Full texts - the future of old prints” will take place in Bonn on 12 February. The findings and desiderata of the DFG project will be presented and discussed there with a broad audience of developers, OCR experts, users and funding agencies.

Kitodo and OCR-D have signed a Letter of Intent to cooperate on the coordinated and sustainable development and provision of OCR software solutions for mass full text digitization. Kitodo is an open source software suite for the digitisation of cultural property and widely used in the library sector.

The OCR-D paper “okralact - a multi-engine Open Source OCR training system (Konstantin Baierer, Rui Dong, Clemens Neudecker) was accepted for the 5th International Workshop on Historical Document Imaging and Processing HIP 2019 (https://www.primaresearch.org/hip2019/) in the context of the ICDAR Conference 2019 in Sydney (https://icdar2019.org/).

On the occasion of DATeCH 2019, the online journal “EuropeanaTech Insights” dedicated its last issue to the topic of optical character recognition.

At the international conference “Digital Access to Textual Cultural Heritage 2019” (DATeCH2019) held in Brussels, the paper on OCR-D entitled “OCR-D: An end-to-end open-source OCR framework for historical documents” was awarded the Best Paper Award. The authors are Clemens Neudecker, Konstantin Baierer, Maria Federbusch, Kay-Michael Würzner, Matthias Boenig, Elisa Herrmann and Volker Hartmann.

The German Research Foundation (DFG) has approved an extension of the OCR-D project for another 18 months. The new funding phase will start in October 2018 and will therefore end in March 2020. This good news allows us to continue supporting the module projects and to consolidate the results. On the other hand, it will also allow the coordination committee’s own work packages to be continued and deepened.

From March 5th to 6th the big kick-off meeting of the module projects took place in the Herzog August Bibliothek in Wolfenbüttel, which officially heralds the second phase of OCR-D.

The call for module projects within the framework of OCR-D can now be found online on the website of the German Research Foundation (DFG) (link to the call)

The coordinating body of OCR-D consists of the Herzog August Bibliothek Wolfenbüttel, the Berlin-Brandenburg Academy of Sciences and Humanities Berlin, in particular the German Text Archive, and now the Staatsbibliothek zu Berlin. In future, the SBB will take over the work of the Bayerische Staatsbibliothek, which withdrew from the project on 31 August 2016.

OCR-D is a coordination project that is aimed at the further development of Optical Character Recognition (OCR) processes for historical prints.