Definition and purpose of optical character recognition

Summary

Optical character recognition (OCR) is the electronic or mechanical conversion of images of typed, handwritten, or printed text into machine-encoded text. The input can come from scanned documents, photos of documents, scene images (such as text on signs), or subtitle text embedded in video. OCR is widely used to digitize printed text so it can be electronically edited, searched, stored more compactly, displayed online, and processed by other computer systems. The purpose of OCR is to enable reliable data entry and information extraction from visual text sources. It supports many real-world workflows such as processing passports, invoices, bank statements, receipts, business cards, and other printed records, and it is also used for tasks like making scanned documents searchable (e.g., searchable PDFs) and extracting text for downstream applications such as machine translation, text-to-speech, key data extraction, and text mining. OCR is a research area within pattern recognition, artificial intelligence, and computer vision, and modern systems can achieve high accuracy across many fonts and image formats.

Key Points

• 1

  OCR converts images of text (typed, handwritten, or printed) into machine-encoded text.

• 2

  It is used to digitize and extract information from documents so text becomes searchable, editable, and usable in automated processes.

• 3

  OCR is a field related to pattern recognition, AI, and computer vision, with modern systems supporting many fonts and input image formats.