Integration of Kitodo and OCR-D for productive mass digitization

• Applicants: Dr. Sabine Gehrlein; Robert Strötgen, since 1/2023; Katrin Stump
• Term: from 2021 to 2024
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 460478737

The project aims for the integration of the free image pre-processing, layout analyzing and text recognition tools of OCR-D as a scalable, distributed web service into the mass digitization workflow and web presentation of Kitodo. Furthermore it creates metrics for quality measurement allowing for an automated workflow optimization of the optical character recognition.

• DFG Programme: Research data and software (Scientific Library Services and Information Systems)
• Participating Institution: Kitodo. Key to digital objects e.V; c/o Sächsische Landesbibliothek
• Ehemaliger Antragsteller: Professor Dr. Achim Bonte, until 7/2022