Reading scanned PDF with different languages

Hey Guys,

Hope you are doing fine in this lockdown. Need a help in on of the POCs I am working on.
I have a scanned PDF and I am trying to read it using Microsoft OCR. The issue here is with the language in the PDF, which could be any language. When I try to read it using OCR it picks up only the English alphabets and skips any other language present in the PDF.

Am I missing something while reading the PDF or going somewhere wrong here. Please help.

P.S. : The POC is to identify the language the PDF is in and I have already figured that part out. I just need to send the output of the PDF to my component.

Dev :slight_smile:

Hi @Devbrath_Rajkhua,
Hopefully this could help you :slight_smile: