Further reading

  • Information on training Tesseract in the EMOP project at: emop.tamu.edu/node/47,emop.tamu.edu/node/54 for the Franken+ tool. ¬†Information on the Franken+ tool at: dh-emopweb.tamu.edu/Franken+/. Publication: Early Modern OCR Project (eMOP) at Texas A&M University: Using Aletheia to Train Tesseract , dl.acm.org/citation.cfm;
  • The following IMPACT reports (included in training materials) describing, among others, experiences on using the Tesseract engine on a diverse set of historical documents.
    • The already mentioned Report on the comparison of Tesseract and ABBYY FineReader OCR engines from PSNC. ¬†PSNC instructions for the Tesseract training process are included in the current training package.
    • Lexicon-supported OCR of eighteenth century Dutch books: a case study (also includes a comparison with Finereader on the same data)