Training launguage

homedweller · Post by **homedweller** » Thu Apr 26, 2018 2:36 pm

Hello,
Now I'm using the newest version of PDF ExChange Editor plus. I was very happy to see that there are a lot of new languages by OCR. I often use and need the Latin language, but I was disappointed when I scanned a Latin page. After using OCR I copied one line after another, but the results were not satisfying. Is it possible to train that language to get better results?

Cheers,
homedweller

Post by **Tracker Supp-Stefan** » Thu Apr 26, 2018 2:40 pm

Hello homedweller,

Welcome to our forums, and thanks for the post!
I am afraid that no - it is not possible to train the OCR engine

Regards,
Stefan

Ovg · Post by **Ovg** » Thu Apr 26, 2018 3:12 pm

2homedweller

Try new Convert->Enhance Scanned Pages

Capture.PNG

Quality of OCR MUCH better.

Post by **TrackerSupp-Daniel** » Thu Apr 26, 2018 5:57 pm

Hi everyone,
I think the main issue here is that Latin is not a Default OCR language, though it should work nicely with English selected, possibly try adding some of the other language to the mix, it may improve those results a bit.
Let us know how the new enhanced scan goes with a few more languages selected!

Willy Van Nuffel · Post by **Willy Van Nuffel** » Thu Apr 26, 2018 8:37 pm

EDIT

Questions moved to a new topic:
viewtopic.php?f=63&t=30862

Ovg · Post by **Ovg** » Thu Apr 26, 2018 9:12 pm

I made quick test with OCR Latin text - it seems not so bad

pdf file was created from png image and now contains text layer.

Post by **TrackerSupp-Daniel** » Thu Apr 26, 2018 11:28 pm

After downloading the Latin Language package, I've found the same results as Ovg here.
Can you confirm that you have the Latin OCR language pack installed?0
https://www.pdf-xchange.com/pdf-xchange-viewer-ocr
Thank you!

Training launguage

Training launguage

Re: Training launguage

Re: Training launguage

Re: Training launguage

Re: Training language

Re: Training launguage

Re: Training launguage