Closed GoogleCodeExporter closed 9 years ago
https://groups.google.com/forum/#!topic/tesseract-dev/0BEK1gIXiIQ
Original comment by shreeshrii
on 11 Nov 2014 at 1:53
I can confirm that this trained data works well with Cyrillic alphabet with one
exception - quotes ("") makes tesseract segfault.
I attached example picture that causes segfault with this command:
$ tesseract test.png out.txt -l srp
Original comment by medicmom...@gmail.com
on 8 Apr 2015 at 4:35
Attachments:
Please create own project repository for your language data (have a look at
tesseract-georgian[1] for example) and post here link.
[1] https://github.com/ddohler/tesseract-georgian
Original comment by zde...@gmail.com
on 12 Apr 2015 at 2:46
[deleted comment]
Project repository for Tesseract-OCR files created for recognition of Serbian
Cyrillic script:
https://github.com/strn/tesseract-serbian
Original comment by puramoca...@gmail.com
on 14 Apr 2015 at 10:56
Thanks. I added to wiki
https://code.google.com/p/tesseract-ocr/wiki/AddOns#Community_training_projects
Original comment by zde...@gmail.com
on 16 Apr 2015 at 7:24
Original issue reported on code.google.com by
puramoca...@gmail.com
on 4 Nov 2014 at 7:41Attachments: