Skip to content

cisocrgroup/PoCoTo

Repository files navigation

The CIS OCR Post Correction Tool PoCoTo

Source code for the Java-based PoCoTo client enabling fast interactive batch corrections of complete OCR error series in OCR'ed historical documents. For a detailed description see the PoCoTo Manual.

The lastest compiled binary can be downloaded here.

References

PoCoTo has originally been written by Thorsten Vobl as part of his master's thesis in computational linguistics at CIS during the IMPACT project.

It has been further developed as a CLARIN-D Kurationsprojekt by Florian Fink and Uwe Springmann at CIS.

Its underlying technology is described in the following publication:

Vobl, Thorsten, Annette Gotscharek, Uli Reffle, Christoph Ringlstetter, and Klaus U. Schulz. 2014. “PoCoTo - an Open Source System for Efficient Interactive Postcorrection of OCRed Historical Texts.” In Proceedings of the First International Conference on Digital Access to Textual Cultural Heritage, 57–61. DATeCH ’14. New York, NY, USA: ACM. doi:http://doi.org/10.1145/2595188.2595197.