My system is Ubuntu in version Jaunty and start using Tesseract GUI. I'm a newcomer to Ubuntu and Unix. I came from windows and mac and there I used Recognita and Rediris.
During last July I was using Kooka on Ubuntu and now when I run it, then appears message: Problem: not found any scanner (but I have the scanner connected). Your system hasn't an installation of SANE (Scanner Access Now Easy), necessary to allow the use of the scanner in KDE. Install and configure properly SANE in your system. (but SANE is installed in version 1.0.14-7. If I do: ~ $ whereis sane, I get the answer: /etc/sane.d /usr/lib/sane /usr/lib64/sane /usr/share/sane /usr/ share/man/man7/sane.7.gz In any case I think it has more future using Tesseract, hasn't it? I want to train Tesseract for my language, Catalan, using tesseractTrainer.py. The procedure that I use is as follows: 1.I have written a page of text with Open Office, Arial font, size 10 ppi and inter-letter spacing 1 pt. 2.Export text to pdf. 3.At the terminal I do: convert -depth 8 -density 300x300 cat.arial1pt10sc300.pdf cat.arial1pt10sc300.tif and: tesseract cat.arial1pt10sc300.tif cat.arial1pt10sc300 batch.nochop makebox 4. I run tesseractTrainer.py and the box not represents the characters $ and @, the character-box is empty but there are in the box file, the other characters are correct. The question is: Do I start properly? Thanks in advance. --~--~---------~--~----~------------~-------~--~----~ You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en -~----------~----~----~----~------~----~------~--~---
