Read Scanned pdf with OCR


I am dealing with confidential documents on an Intranet comp so I can’t use an engine that need online or cloud access.

I tried
OmniPage OCR
Tesseract OCR
but I don’t understand the options like
Input: The default is image. Are there other inputs?
Profile: What does None, Scan, Screen, Legacy mean?
Scale: What is this for?
Language: What is this for?

Thank you!


Check below documentation for Tesseract OCR

Mark as solution if this helps