OCR - ABBYY FineReader (embedded) - how to get support for Indian languages (e.g. Hindi or Marathi)?

[Jonas]

I am working corporate cases from time to time where I have a need to OCR-process pictures and pdf documents containing different Indian languages. As far as I can tell, there is no support for e.g., Hindi or Marathi in the built-in ABBYY FineReader (embedded) function the Intella Pro.

Is there a way to expand on supported languages in the embedded OCR function?

Kind regards,

Jonas 

[Jacques B]

I'm not sure what ABBYY FineReader uses for OCR (in-house, open source, or combination). Tesseract is a free OCR solution that does support those languages.

https://tesseract-ocr.github.io/tessdoc/Data-Files-in-different-versions.html

I don't know if there is a way to use a crawler script to use an external OCR tool. Or alternatively (less desirable of course) is to export those items, OCR them externally and bring them back in as new items.

[Jonas]

Hi Jacques, Thank you for your reply. I am already using an external "free" package to partly solve the need from time to time - what I was looking for was a reply on IF Intella built-in capabilities can be expanded on. Since no-one else have responded to this, perhaps I will have to close this search for the time being. Kind regards, Jonas

[Jacques B]

OK. I know there are admins on here. I'm not sure if they work for Vound, or are volunteers. Hoping one of them can provide you with an answer.

Alternatively, you can submit a support ticket to them. For that, they are responsive. Where this is a community board, it may rely more on community members vs Vound staff.

[igor_r]

Hello Jonas ,

ABBYY doesn't support Hindi or Marathi. You would need to look for an alternative OCR solution.

Please look at the using of external OCR tool section in the user manual: https://www.vound-software.com/docs/intella/2.7.1/#_using_an_external_ocr_tool

Basically you can export the items that you need to OCR to plain text files, then run the OCR tool that supports Hindi and then import the OCRed files back to Intella. That would be the best option in your case.