Well, I have managed to significantly increase the quality of the output by rescaling my input photo (I multiplied it by 3 on width and height) but I'm still having some issues with recognizing some characters.
For instance, capital i and l are often misread, same goes with O and 0, 5 and s etc. I would like to force tesseract to find the most appropriate word in the language dictionary I'm using, does anyone knows if that's possible ? Would there be any other things I could do to improve the quality of the OCR ? (I've thought of skewing but I can't find anything online and it doesn't seem to be that big of a problem) Thank you for any help -- 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 http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/817440b7-737b-4da7-8dd4-4ac79399ad21%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
