OCR

Optical character recognition or optical character reader is the electronic or mechanical conversion of images of typed, handwritten or printed text into machine-encoded text, whether from a scanned document, a photo of a document, a scene-photo or from subtitle text superimposed on an image. Wikipedia

In regards to RPA projects there are varying levels of OCR choices available:

• Core, basic OCR - provides bots the ability to scrap text from images, pdfs. not geared towards template (i.e. invoice) document data extraction
  

• Advanced add-on/3rd party applications - typically support full OCR needs. Major vendors have plug-n-play addons/widgets/app store components for major RPA platforms. Bot calls OCR app, OCR gets data and sends it back to bot for processing.
  

• Cloud OCR services - added advantage of SaaS, no on-prem overhead. typically access via REST APIs via a call from bot. Cost varies but typically by volume/transactions.
  

Advanced add-on/3rd party applications

• ABBYY

• Adobe Acrobat Pro DC

• AntWorks

• BluePrism Decipher

• Readiris

• Rossum (Invoice focus)

• Tesseract - Google, open source

Cloud OCR Services

• ABBYY

• Google

• Microsoft

• Amazon

• IBM