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 coordination committee of OCR-D met for the first time with the ten module project participants to get to know each other and to present the work done and planned on both sides. In short presentations, the project application contents were presented and connections between the module projects and the coordination committee were sought. During the personal exchange in the World Café as well as during the joint dinner, first project-strategic discussions could be initiated, which will accompany us in the near future.

Of the more than 20 project proposals received in response to the DFG call for proposals in March 2017, eight module projects were approved at the end of the year:

Scalable methods of text and structure recognition for the full text digitisation of historical prints: Image optimisation German Research Center for Artificial Intelligence (DFKI)

Scalable methods of text and structure recognition for the full text digitisation of historical prints: layout recognition DFKI

Further development of a semi-automatic open-source tool for layout analysis and region extraction and classification (LAREX) of early printed books University of Würzburg

NN/FST - Unsupervised OCR Postcorrection based on Neural Networks and Finite-state Transducers Leipzig University

Optimized use of OCR processes - Tesseract as a component in the OCR-D workflow University of Mannheim

Automatic and semi-automatic post-correction of OCR-recorded historical prints Munich University

Development of a model repository and automatic font recognition for OCR-D Leipzig University, Erlangen University, Mainz University

OLA-HD - An OCR-D long-term archive for historical prints SUB Göttingen, GWDG Göttingen

The module projects usually have a duration of 18 months, a public final workshop is planned for June 2019. Until then, the coordination committee will organise two project-internal developer meetings to discuss the previous versions of the work. An insight into the development can also be found on the GitHub page of OCR-D: https://github.com//ocr-d In addition, the coordinating committee and the module projects are in regular exchange via video conferences during this intensive work phase.

Further details on the individual module projects and later on the developer meetings will follow on the OCR-D website.

We are looking forward to working together!

For questions and suggestions: contact