Instead of retraining font, you should focus on pre-processing image. One option that worked in this particular case was resizing the image.
I did (tesseract was able to read the image) $ convert a.png -resize 170% b.png $ tesseract b.png stdout -l eng --tessdata-dir /usr/share/tesseract-ocr/tessdata Error in pixGenHalftoneMask: pix too small: w = 301, h = 53 Kaushik Ashish On Fri, Jul 22, 2016 at 1:00 PM, ShreeDevi Kumar <[email protected]> wrote: > https://github.com/tesseract-ocr/tesseract/wiki/ImproveQuality > > ShreeDevi > ____________________________________________________________ > भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com > > On Wed, Jul 20, 2016 at 6:37 PM, koushik v <[email protected]> wrote: > >> Hi, >> >> I took a screenshot of text with font helvetica neue which can be seen in >> the attachment.Then i trained tesseract using the helvetica and helvetica >> nue fonts available in mac and generated a training data. I hoped that >> tesseract would identify the text perfectly using the trained data but it >> did not work as can be seen in the screenshot. >> >> Can anyone suggest what i am missing here to make this work? >> >> Thank you >> >> -- >> 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/fc74c251-3603-4fbc-9aa2-6e1bea96fc75%40googlegroups.com >> <https://groups.google.com/d/msgid/tesseract-ocr/fc74c251-3603-4fbc-9aa2-6e1bea96fc75%40googlegroups.com?utm_medium=email&utm_source=footer> >> . >> For more options, visit https://groups.google.com/d/optout. >> > > -- > 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/CAG2NduVKi5px%2BFQ_-L7pahi9%3DxZCrD%2B3vVW_nouJWYAr%3DhQhbw%40mail.gmail.com > <https://groups.google.com/d/msgid/tesseract-ocr/CAG2NduVKi5px%2BFQ_-L7pahi9%3DxZCrD%2B3vVW_nouJWYAr%3DhQhbw%40mail.gmail.com?utm_medium=email&utm_source=footer> > . > > For more options, visit https://groups.google.com/d/optout. > -- 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/CAJSNBUak9EE5RsPPEV%3D--bz5qkPr-NWpy3XXvnvtzNGD5eOdZQ%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
