OCR-D

OCR-D

Integration of Kitodo and OCR-D for productive mass digitization

A retrospective national bibliography of early modern literature from the German-speaking world is being compiled with the indexes of 16th-18th century prints published in the German-speaking world (VD 16, VD 17, VD 18). In order to facilitate research access to these texts, great concerted efforts have been and are being made to provide full digital copies or key pages for the individual listed titles.

This is where the DFG-funded OCR-D project comes in, the main aim of which is the conceptual and technical preparation of the full-text transformation of the VD. The task of automatic full-text recognition is broken down into its individual process steps, which can be reproduced in the open source OCR-D software.

Informationen

Management
Robert Strötgen, M.A.
Dr. Jan Linxweiler

Runtime
Juni 2021 - Mai 2023

Funded by
Deutsche Forschungsgemeinschaft (DFG)

Webseite
https://www.bib.uni-mannheim.de/ihre-ub/projekte-der-ub/ocr-d-kitodo/

Kitodo and OCR-D implementation project

In cooperation with the SLUB Dresden and the Mannheim University Library, the Braunschweig University Library is participating in the project to mutually integrate OCR-D and Kitodo. OCR-D is to be made usable for distributed operation on a web server. Full texts can then be displayed in the DFG viewer and made available "on demand".

Another goal is to optimize and increasingly automate the workflow for OCR-D. Among other things, community workshops will be held and a prototype structure for a generally available OCR service within the Kitodo community will be created.

Cooperations

Further links