> >it would be helpful to explain by sreenshots, if there is no objections. See my previous eMail.
> > Really interesting points. Since I am not programmer nor developer, it is > > difficult to understand the above points. Is it possible to explain with > > help of screen shots of the sample image. Your "training" picture is okay, i'm more talking about the "real" pictures you're going to feed tesseract for recognition. > Generally, with help of Irfanview software, images are ensured that it will > have 300 or 600 dpi and saved as uncompressed tif. > I hope tesseract 3.0 will have provision/feature of "auto- build > histogram" That's not a really good idea. Tesseract core can't provide such feature, since it's really linked to the user's documents. However, providing a surounding layer to the core which offers an API which allows such things can be okay. Anyway, i won't be able to help you more than what's been said already. i hope you'll succeed doing your things, i strongly suggest you that you find someone who can help you program simple C++ pre-processing based on advices. Pierre. -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to [email protected]. To unsubscribe from this group, send email to [email protected]. For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en.
