Ocr

Part of speech: noun

Definitions

1. A technology that converts different types of documents, such as scanned paper documents or images, into editable and searchable data; a process used to recognize and digitize printed or handwritten text from visual inputs; software or systems that analyze and translate visual text content into computer-readable characters
2. A method for extracting and converting text in paper-based or digital images into machine-encoded text; a system that enables the recognition of letters and words from scanned documents; a tool that transforms visual representations of text into editable and searchable formats
3. A computational technique to scan and interpret text from physical documents or image files; an application allowing the identification and digitization of printed characters; a process for converting textual images into editable electronic text for further use or analysis

Etymology: OCR is an abbreviation of "optical character recognition," the technology that reads printed or handwritten characters from an image and converts them into editable text. The initials were in use by the 1950s, when the field was taking shape, and the term was rooted in the earlier idea of optical reading machines that could scan a page and interpret its letters. The three words describe exactly what the machine does: it uses light (optical) to pick out marks (characters) and identify which symbol each one is (recognition). Like many technical coinages, the term was built from ordinary English words rather than borrowed from another language, so there is no older foreign source to trace. Its history is best understood as a sequence of practical descriptions. Early machines in the 1950s were designed to read specific typefaces, and the name stuck even as the technology grew to handle many fonts, scripts and eventually handwriting.