This paper might also be relevant to you: http://www.imlab.jp/cbdar2007/proceedings/papers/O1-1.pdf But it might be to much for the RaspberryPi.
You could binarize the image with this method, then do OCR on it. Am Montag, 9. Juni 2014 16:02:33 UTC+2 schrieb Emerson Walsh: > > Anybody willing to help? > > > On Tuesday, June 3, 2014 3:19:24 PM UTC-4, Emerson Walsh wrote: > >> Hi, >> >> I have been trying to use tesseract-ocr on my Raspberry-Pi to read images >> I have saved. I have had decent success so far but hope to take this much >> further. My main goal is to have it scan an image I give it, search for a >> specific object in the picture (a square with a 4 digit number inside), and >> once it finds it, use OCR to send back the numerical data (the number >> inside the object). As of now, I have really only been working with >> different ways of manipulating the image I give it, so it is easier for >> tesseract to read. >> >> Do you have any advice for me moving forward (especially with a way to >> scan an image for the specific object)? Is this possible? Any specific >> software you know that could help me? >> >> I really appreciate any feedback at all. >> >> >> Thanks, >> Emerson >> > -- 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/a137cb0b-f524-4dea-b5ba-dd5b1a3c65f9%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
