DFG funds Font Group Recognition for Improved OCR

Symbolic picture for the article. The link opens the image in a large view.

We are pleased that the German Research Foundation (DFG) funded our project “Font Group Recognition for Improved OCR”. It will be part of Phase III of OCR-D, the German initiative for OCR development. In total, FAU will receive 210.000 Eur for 24 months.

This project aims to improve OCR for books from the 16th to 18th century by facilitating the use of general, font-group-specific or multi-font-group-specific OCR models, i.e., OCR models are trained for one or multiple font groups. To achieve this, we follow three main objectives:

  • Development of a fine-granular font group recognition tool
  • Generation of font-group-specific OCR training-data
  • Development of font-group-specific OCR models

This project is a joint project by the Pattern Recognition Lab (FAU) and the Gutenberg Institute for World Literature and Written Media, Section Book Studies (JGU Mainz).

Image credits: Johann Zündell: Responsum (…). [Halle: Salfeld, 1696]. Halle, Universitäts- und Landesbibliothek Sachsen-Anhalt: Pon Zf 5145, QK. (VD17 7646084S), p. 7.