Optical Character Recognition (OCR)
Also called: OCR
Optical character recognition (OCR) is computer vision technology that converts printed, handwritten or scanned text inside digital images and PDF files into machine-encoded, searchable text. Modern OCR uses deep learning to parse complex business documents accurately: invoices, unstructured PDF files, legal contracts and financial receipts. It is the entry point for enterprise document processing, because nothing downstream can act on a document until its contents are readable data.
In practice
OCR is what turns a paper-driven back office into an automatable one, so it is usually the first step in a document workflow business case rather than the interesting part of it. Test it on your worst documents, not your cleanest: accuracy on a crisp typed invoice tells you nothing about a scanned handwritten delivery note.