Problem Recognizing Numbers

I'm using v 3.01 on Windows 7 to perform OCR on another program. I don't have access to the fonts the program is using, so I trained tesseract using some screenshots, and so far the text recognition is far better than I expected. However, when I try to process a screenshot that contains only a few

Re: Any one successfully build Tesseract 3.0.1 under MSYS+MinGW?

٩١#2/02/2012 13:40, "asmwarrior"٩٦ escribió: > > Hi, all. > I'm trying to do this, but failed. > > The first thing I do is build leptonica-1.68 and installed to /mingw (the MinGW folder is mounted to /mingw under MSYS) > > Then I try to run the configure٦٠ under Tesseract-ocr folder, and it failed

Re: Decreased accuracy after training for specific characters

I think you are right - I don't think the sample box data provided for download can be the same data that is used by google to create the trained data. On Feb 12, 12:42 pm, Zdenko Podobný wrote: > Hi Chris, > > I have the same experience - that leads me to conclusion it does not > make sense to t

Re: Any one successfully build Tesseract 3.0.1 under MSYS+MinGW?

On Sun, Feb 12, 2012 at 6:40 AM, asmwarrior wrote: > > ** > > On Thursday, February 9, 2012 5:47:17 AM UTC+8, zdpo wrote: >> >> Hi, >> >> Have a look at >> https://github.com/zdenop/**tesseract-mingw >> >> I was/am testing building tesseract by cmake...

Re: Decreased accuracy after training for specific characters

Hi Chris, I have the same experience - that leads me to conclusion it does not make sense to train "common" fonts... I think google use different process (more detailed; more/other tools?) comparing to information available on wiki... IMHO situation is improving with each release, so I wait f