What is Optical Character Recognition OCR Software?

Optical Character Recognition (OCR) software is used to extract information from an electronic document image, whether originally in electronic format or a scanned paper document. OCR software is technology solely used for extracting machine-printed text, and is an essential tool for any organization burdened by manual data entry.

Though many may think optical character recognition software is synonymous with all data extraction capabilities, it is actually only a piece of any data capture solution because it cannot read handwritten text, check boxes and radio buttons or barcodes. These types of data can be handled by more sophisticated technology, often called Intelligent Capture software, which include capabilities for all of the following types of data:


  • Optical character recognition (OCR) – Reads machine-printed characters
  • Intelligent character recognition (ICR) – Reads hand-printed characters
  • Optical mark recognition (OMR) – Used to determine a selection from a list of choices (i.e., check boxes and filled circles)
  • Barcode recognition – Reads data from barcodes located on the document

In addition to capturing the data, capture solutions are powered by intelligence built into each solution to help the software understand where to extract information from the documents, as well as validate the pulled information within your existing ERP.

Learn more about capture solutions in our Learn ECM / “The Building Blocks of Capture” section or learn more about our Brainware Intelligent Capture solution.