Hi Rolf, thank you for your response. Is this the "right" way? I read that I should rather use proper settings in tesseract than doing manual processing.
Are smaller texts a problem in general? Am Freitag, 6. Mai 2016 06:41:06 UTC+2 schrieb Rolf Mertig: > > If you resize with convert from ImageMagick (or any other tool): > convert ocr.jpg -resize 150% ocr2.jpg > then > tesseract ocr2.jpg ocr2 ; cat ocr2.txt > gives > ABC-DEF > > > Am Donnerstag, 5. Mai 2016 14:23:13 UTC+2 schrieb Christian Koch: >> >> I try to recoginze product codes written in images. >> The results in tesseract 3.04.00 are pretty bad. Even when I try a >> primitive example (see attachment) it won't work. >> >> Instead "ABC-DEF" I get "AECVDEF" >> >> The example works *flawlessy* in gocr but guess I'm just using wrong >> settings or something similar in tesseract. >> Or is tesseract in general not designed to recognize "random strings" >> and I should rather use another tool (recommendations?) for this case? >> > -- 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/d2a5d7fb-2dc9-4efe-b645-9f5fd48d4002%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
