Thank for your answer Mario. I'll definitely give training tesseract a try.

John

----- Original Message ----- 
From: "Mario César" <[email protected]> 
To: [email protected] 
Sent: Wednesday, August 7, 2013 10:07:11 AM 
Subject: Re: [Mayan EDMS: 612] Most reliable OCR? 


2013/8/7 John Wells < [email protected] > 



I'm evaluating Mayan and like what I see so far. However, I'm finding 
Tesseract's OCR to be pretty inaccurate. What, in your experience, is the most 
reliable OCR engine out there? We're willing to buy a commercial engine if 
necessary. I've googled a bit and have a call set up with ABBYY, but would love 
to have some input on what others have used, or if there's a way to make 
tesseract more reliable. 




Tesseracts is the best opensource OCR library I had work with. Others are just 
to simple or output unusable results. 

I will recommend you that learn about Training 
https://code.google.com/p/tesseract-ocr/wiki/TrainingTesseract3 In my case I 
had a lot of common formatted documents, the first try was unacceptable, but 
after doing some training work the results where pretty much 90% accurate. 




-- 

--- 
You received this message because you are subscribed to the Google Groups 
"Mayan EDMS" group. 
To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected]. 
For more options, visit https://groups.google.com/groups/opt_out . 



-- 

--- 
You received this message because you are subscribed to the Google Groups 
"Mayan EDMS" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].
For more options, visit https://groups.google.com/groups/opt_out.


Reply via email to