Pega Marketplace Terms of Use

Pega OCR

The Pega OCR component lets you analyze and highlight content extracted from your images.

By using or submitting listings via the Pega Marketplace, you agree to our Terms of Use.


The Pega OCR component brings optical character recognition (OCR) functionality to Pega Platform applications. Used together with Intelligent Virtual Assistant (IVA) for Email, this component extends the channel to extract image-based text from email attachments across several filetypes, including PDFs.

The extracted text is subsequently analyzed by the email channel's Natural Language Processing model to identify entity values within the attachment. When an entity is identified, the component highlights the appropriate area within the original attachment file to visually indicate entity values found in the document.

If you want to make use of OCR capabilities outside IVA for Email channel there is an extension point available that allows Pega Platform to invoke the Pega OCR component by using an API.

Note: The Pega OCR component .zip file that you download contains the OCR component and a .jar library that you must import to Pega Platform. For more information, see the Installation Guide. This component is currently only available on-prem or customer managed clouds.

Key Features

  • Use OCR capability to obtain content from images JPG, PNG, TIFF or included in PDF files and convert it into text to be used in Pega Platform applications.
  • Highlight extracted entities from the email attachments handled by Intelligent Virtual Assistant (IVA) for Email.





Compatible With

Pega Platform

Last updated

July 9, 2020

Related Topics

Low-Code App Development