Project homepage: github.com
Download current (devel) source: tar.gz or zip
Licence: Code is released under Apache License, Version 2.0. Other files (e.g. fonts) can have its own licenses.
This is attempt to create python scripts for automatic tesseract traning. Scripts are based on script from project tesseractindic tesseract_trainer
- Python (tested on 2.6.6)
- tesseract (tested on 3.00; at the moment it do not work with 3.01)
python generate.py -font <font name> -l <language> -s <size> -a <input alphabet directory>
This generate testing images and run tesseract traning on it.
Example:
$ python generate.py -font mitra -l beng -s 10 -a beng.alphabet/
$ python generate.py -font Courier -l eng -s 10 -a eng.alphabet/
$ python generate.py -font Arial -l slk -s 10 -a slk.alphabet/