OCR new Language

[RobertH]

I need to use the OCR component to do an OCR on newspapers. As I am in Sough Africa, the OCR also needs to run on the Afrikaans newspapers.

Now I assume that there is no language plug-in for Afrikaans. So what will happen if I try and run the OCR on an Afrikaans page with English specified as a language? Will it do an OCR on the page, ignoring the words that it does not find a match for? Is there a way for me to create a dictionary file for Afrikaans?

[Loïc]

Hi Robert,

Unfortunately we do not provide support for creating new dictionary. Next version of the engine will come with a bunch of new languages, today I am not able to say if Afrikaans will be available or not.

Thank you for your comprehension.

kind regards,

Loïc

[Mcb2000]

Hello Loïc

Do you have a new estimate on when that version will become available?

Regards,
Martin

[Loïc]

Hi Martin,

We have to finish first our next 2 Plugins (64-bit PDF & Annotation), new Tesseract 3 engine gateway will follow. This will takes probably between 3 and 6 months.

Kind regards,

Loïc