HFST-TESSERACT: Open-source Transducers and OCR
June 2-6, 2014, a workshop will be held at the University of Helsinki featuring open-source resources in Optical Character Recognition.
Purpose: Work with the integration of finite-state transducer descriptions and the OCR engines "Ocricola" and "OCRopus"

The workshop will ideally have about 15 participants.
Organizers include Miikka Silfverberg (Integrating HFST transducers with Tesseract), Tommi Pirinen and Jack Rueter. Finance from Kone Foundation, Helsinki.


Here's a link to the modified Tesseract code:
https://sourceforge.net/projects/ocricola/
And here's a link to a page describing how you can train your own models:
https://sourceforge.net/p/ocricola/wiki/AddNewLanguage/


Contact Jack Rueter: First name dot last name at helsinki dot fi.


Last modified: Tue Mar 25 9:26:17 EEST 2014