Hi! Thanks for the response! That's is much better! COuld you please tell me which tool you used to convert the image to PDF but considering the text as text in the PDF and not just an image?
El viernes, 20 de octubre de 2017, 7:40:32 (UTC-3), zbgns escribió: > > Some improvements of the image are necessary before you apply OCR on it. > Please look at the attached file. The output is maybe not a complete > garbage, although the results are still not impressive, as the input image > is distorted too much (especially the shadow seems to be challenging). > > > W dniu czwartek, 19 października 2017 21:08:37 UTC+2 użytkownik Fabian > Angeloni napisał: >> >> Hi! >> >> I'm trying to do the OCR for the attached image, but the result are just >> nonsense characters... I tried with some preprocess like change to gray >> scale, denoise, improve DPI, etc... but the results are the same... >> The issue is when I'm doing this taking the image directly from a >> celphone using a webapp. >> >> Any help? >> >> the command I'm using is: >> tesseract-l spa inputoutput >> >> Regards >> > > -- 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/b21e1064-ebe1-4710-8a63-65c65de4807d%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
