Jump to content
Sign in to follow this  
Vachy

Tesseract accuracy

Recommended Posts

Vachy

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:

Posted Image

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

Share this post


Link to post
Share on other sites
evilertoaster

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' :idea:

I can only recommend getting the most up-to-date version of tesseract or trying one of the other OCR libraries (Google search!)

Share this post


Link to post
Share on other sites

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 account

Sign in

Already have an account? Sign in here.

Sign In Now
Sign in to follow this  

×

Important Information

We have placed cookies on your device to help make this website better. You can adjust your cookie settings, otherwise we'll assume you're okay to continue.