ImageEn for Delphi and C++ Builder ImageEn for Delphi and C++ Builder

 

ImageEn Forum
Profile    Join    Active Topics    Forum FAQ    Search this forumSearch
Forum membership is Free!  Click Join to sign-up
Username:
 Password:
Save Password
Forgot your Password?

 All Forums
 ImageEn Library for Delphi, C++ and .Net
 ImageEn and IEvolution Support Forum
 OCR does not correctly recognize some words		  New Topic  Reply to Topic
Author Previous Topic Topic Next Topic  

distrito

Spain
1 Posts
Posted - Sep 16 2024 :  10:06:07  Show Profile  Reply
I tested the attached image with the most recently OCR Demo (IEVision 8.1.3.0).
Some words are not recognized correctly by the OCR, for example, the word FG073 is recognized as FGO073.

attach/distrito/202491610534_ocr.png

xequte

38531 Posts
Posted - Sep 17 2024 :  00:38:31  Show Profile  Reply
Hmm, that is a curious result. If I use the "Fast" Tesseract eng.traineddata, I get the expected result:

FG073

FG037

FG037

FG101

FG114

FG037
FG184

FG095
FG184


But with "Best" it is somehow tripped up by this image. You might want to put that to the Tesseract community for guidance.

Nigel
Xequte Software
www.imageen.com
Go to Top of Page
  Previous Topic Topic Next Topic  
 New Topic  Reply to Topic
Jump To: