Link to home
Start Free TrialLog in
Avatar of Yann de Champlain
Yann de ChamplainFlag for Canada

asked on

Need help creating .traineddata for Tesseract OCR on Linux

I need help creating traineddata for Tesseract.  We need to train it for Car VINs.  Linux server got it installed on V4 and I creayed a set of 12 pictures to work with.
In the end, it's to be used in PHP on a website. Everything is completed except it's not accurate enough using only english traineddata.

The existing documentation is too confusing for us.  

I am looking for more specific instruction or someone we could hire for a few hours to help on this.

Out traineddata is located in /usr/share/tesseract/tessdata/
ASKER CERTIFIED SOLUTION
Avatar of dfke
dfke

Link to home
membership
This solution is only available to members.
To access this solution, you must be a member of Experts Exchange.
Start Free Trial
Avatar of Yann de Champlain

ASKER

thanks a lot.  I'm still not able to do it, but the explanations are indeed very good.  I'll find a freelancer to help using those.