c++ - Tesseract setVariable whitelist for another language -
tesseract setvariable whitelist works ok english language language illustration utilize recognize digits , letters image (excluding special characters &*^%! etc)
myocr->setvariable("tessedit_char_whitelist", "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz");
but can't same thing russian language
myocr->setvariable("tessedit_char_whitelist", "0123456789абвгдежзийклмнопрстуфхцчшщъыьэюяАБВГДЕЖЗИЙКЛМОПРСТУФХЦЧШЩЭЮЯ");
is there different principle? because don't work. instead of determined characters recieve digits in output, tesseract ignores russian letters set whitelist. blacklist didn't work too. there way rid it? thanks.
so reply utilize symbols unicode codes in whitelist, don't know how exactly
c++ ocr tesseract
No comments:
Post a Comment