Hello, As mentioned in divers sites in Internet . Tesseract is the best open source OCR existing nowadays and detecting too much languages. But, for recognizing Arabic, it's not so good : so i tried it myself and even with tessdata containing ara.traineddata i didn't get any exact arabic characters. So i plan to build my own ara.traineddata : i follow this tutorial Training Tesseract <https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract> and start to generate all the files necessary to finally combine them and get ara.traineddata. I stopped in the dictionary data because i didn't get it : in the tutorial they said that's optional but i want to create my own dictionary containing around 1000 words that i'll surely use it with tesseract but i didn't understand how to do it because they mentionned UTF-8 so i have to put all the words in a separate line in a file .txt then how i have to formatted as UTF-8?
May be it's a weird question but hope you will give me answer. Thanks. -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To post to this group, send email to [email protected]. Visit this group at https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/8c6ab4f1-66ec-4756-a6f5-f7569bb39a35%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
