Vachy Posted May 7, 2010 Share Posted May 7, 2010 Dear all,I used to make some autoit script and this time i would like to get information on a java window.I found out a way to use OCR and tesseract was the one i found out on the forum.I am able to make it run but the accuracy is somewhat totally screwed.command used:$Code_opt[9] = _TesseractScreenCapture(0,"",1,5,16,597,1229,1012,1)For example here is a result i have:Is there a simple way to enhance tesseract accuracy?I tried to change the multiplier parameter but even if that solve the problem for this example, i get then errors on other letters...Or if there is another OCR that is more accurate it would be great.Regards,Vachy Link to comment Share on other sites More sharing options...
evilertoaster Posted May 7, 2010 Share Posted May 7, 2010 An ongoing endeavor- http://www.autoitscript.com/forum/index.php?showtopic=42691 OCR's that can depict a '1' from an 'I' with 100% accuracy do not exist AFAIK. I'd be happy that it found the 'B' and not an '8' I can only recommend getting the most up-to-date version of tesseract or trying one of the other OCR libraries (Google search!) Link to comment Share on other sites More sharing options...
Recommended Posts
Create an account or sign in to comment
You need to be a member in order to leave a comment
Create an account
Sign up for a new account in our community. It's easy!
Register a new accountSign in
Already have an account? Sign in here.
Sign In Now