Project Details
Projekt Print View

Coordinated Funding Initiative for the Further Development of Optical Character Recognition Processes

Applicants Professor Dr. Peter Burschel, since 8/2016; Professor Dr. Martin Grötschel, since 12/2015; Barbara Schneider-Kempf, since 11/2016
Term from 2015 to 2020
Project identifier Deutsche Forschungsgemeinschaft (DFG) - Project number 274863866
 
The coordination project (= phase 1) aims to develop processes and create guidelines to establish a highly efficient workflow for as well as a far-reaching standardization of OCR related processes and metadata. In addition, it proposes to draw up a plan for the eventual conversion of the entire written German cultural heritage into machine-readable form (structured full text). Against this background the applicants will establish a suitable infrastructure to coordinate and curate projects in the second phase of the DFG call for proposals (realization phase) and submit drafts for this call to the DFG within six months. This will ensure that in areas where good results can be expected in the short term, progress will be made swiftly. Furthermore, the project will benefit from experience gained in these projects by being able to evaluate and document processes and standards in view of their practical applicability. In detail the following objectives will be pursued in the coordination project: a) describing basic features and modules of OCR processes, b) developing guidelines, recommendations and concepts for setting OCR processes to work, c) drawing up a master plan for full-text conversion that is based on the inventories of imprints of the German speaking area and providing recommendations for project clusters in phase two and finally d) giving advice to and coordinating these projects in close cooperation with the advisory board of the project and experts in the field.The overall project (including the projects in phase two) will result in a consolidated process that will permit conversion of all digital items of written German cultural heritage from the 16th up to the 19th century according to established OCR standards. In addition, it will provide a comprehensive documentation that addresses all technical, information science and organizational issues and challenges related to this very process.
DFG Programme Research data and software (Scientific Library Services and Information Systems)
Ehemalige Antragsteller Dr. Klaus Ceynowa, until 11/2016; Professor Dr. Helwig Schmidt-Glintzer, until 8/2016; Professor Dr. Günter Stock, until 12/2015
 
 

Additional Information

Textvergrößerung und Kontrastanpassung