Распознавание текста (Optical character recognition - OCR) в ОС GNU/Linux ====== Tesseract ====== tesseract -l rus page.png page_text tesseract -l rus --psm 4 page.png page_text ====== Полезные ссылки ====== ===== Программы ===== [[http://code.google.com/p/tesseract-ocr/|Tesseract-OCR]] [[https://groups.google.com/forum/?fromgroups#!msg/fido7.ru.linux.chainik/B75ktOsClnA/4UgX7tsiiOwJ|Распознование русского языка при помощи tesseract OCR]] [[http://openocr.org/|OpenOCR.org]] [[https://launchpad.net/cuneiform-linux|Cuneiform]] [[http://sourceforge.net/projects/oocr/|OOCR]] [[http://www.gnu.org/software/ocrad/ocrad.html|Ocrad (GNU OCR)]] [[http://claraocr.org/|ClaraOCR]] [[http://lem.eui.upm.es/ocre.html|ocre]] [[http://jocr.sourceforge.net/|GOCR]] [[http://sourceforge.net/projects/kognition/|Kognition]] ===== On-Line сервисы ===== [[http://www.free-ocr.com/|FreeOCR]] on-line [[http://www.onlineocr.ru|OnlineOCR]] [[http://www.newocr.com/|NewOCR]] ===== Дистрибутивы (серверы) ===== [[http://www.watchocr.com/|WatchOCR]]