This paper <http://www.m.cs.osakafu-u.ac.jp/cbdar2007/proceedings/papers/O1-1.pdf> suggests a binarization approach that might be helpful with your imagery. Unfortunately you need to implement it on your own in a preprocessing step, since Tesseract only uses Otsu's method for binarization. Thus the bad results.
Am Freitag, 27. Juni 2014 12:47:55 UTC+2 schrieb morteza neishaboori: > > Hello, > I want to train tesseract to detect words in such images in the link below! > > https://drive.google.com/folderview?id=0B3dLM0w0EeD-RFZVc1NjaGNqUlE&usp=sharing > > I tried but it was not successful! now I will be happy if somebody can > give me some hints if it's at all possible to do this with tesseract?! > -- 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/c149a5a9-f72c-4fa8-8f78-9432715d380c%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
