Blog archive

Wednesday, October 30, 2019

A good searchable PDF software should support Multilingual OCR. OCRvision's text recognition feature can detect a wide variety of languages and can detect multiple languages within a single scanned document. You can see the complete list of supported OCR languages here. This means you can successfully create a searchable PDF from a scanned PDF or scanned image with more than one language in it.

In order to do Multilingual OCR using OCR vision, do the following steps;

  • Open the OCRvision user interface
  • Click on languages tab on the left-hand side (see the screenshot below)

 

multilngial OCR

      Fig 1: OCRvision language configuration interface  

Click on the languages you want in your multi-language OCR process and check the tick box. Once a language is enabled the text will turn blue. If you want to disable the language you can uncheck the tick box. There is a search box on the right-hand side of the interface where you can search for a particular language. 

Once you select and tick the language, it will automatically get updated and that language will be enabled for Multilingual OCR.

DONE. Now all you have to do is copy your scanned pdf document with multiple languages in the pre-configured "magic folder".

              Fig 2: OCRvision magic folder configuration interface 

 After a couple of seconds, a searchable PDF with multiple languages will be generated in the magic folder automatically. You can see the "currently processing file" which is being converted to a searchable PDF in the bottom left notification strip as in the screenshot above. As I said earlier, You don't have to do any manual button click. OCR vision is a searchable PDF  OCR automation software. It will create a searchable PDF automatically

 

Leave your comment