Your image is 96 dpi. Increase the dpi to 300 and try. Preprocess the image to remove the boxes around letters, if possible.
See https://github.com/tesseract-ocr/tesseract/wiki/ImproveQuality ShreeDevi ____________________________________________________________ भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com On Fri, Oct 20, 2017 at 1:24 PM, 朱裕清 <[email protected]> wrote: > This is my target image: > >  > > Actually my question is similar to [this post](https://stackoverflow. > com/questions/4944830/how-to-make-tesseract-to-recognize- > only-numbers-when-they-are-mixed-with-letter). But I don't know why the > following answer will lead to another direction. I mean, I just hope to get > those digits with high degree of confidence. Such as I can do this with > another language > >  > > Then I can just keep those degree of confidence with a threshold `0.9`. > But now I hope to use *Tesseract* to do this. > > First, I train a *number.traineddata* just for recognizing number. You can > get it [here](https://1drv.ms/u/s!Aumb0ijJibxOi1KVXFjwDzOVRQrm). > > > tesseract.exe target.jpg stdout -l number --oem 0 -psm 6 > > >  > > Note I will get all digits which include high confidence and low > confidence. Can we recognize the number and get the degree of its > confidence? I cannot find any information to implement it. If *Tesseract* > cannot do it. Any other method based on **C++** can implement my target? > Could anyone can give me some information for it? > > -- > 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/273d9f86-39ce-42fe-8934-781f2103e4fa% > 40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/273d9f86-39ce-42fe-8934-781f2103e4fa%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/CAG2NduWsYBa10DrvxLJq3Rggtqs41h4rJ2A7uC9JXA5HGCmAgw%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
