INFO: What is OCR

OCR or Optical Character Recognition is the act of translating a printed, physical document to electronic text through a scanner. Typically, when a document is scanned, it is scanned as an image and cannot be changed or edited. When using an OCR-compatible scanner and OCR software, a document or page of text can be scanned in to the OCR software, which then converts the text to an editable document, typically in Microsoft Word format or as an Adobe PDF file, depending on the software and the settings chosen.

Many Optical Character Recognition programs convert physical documents in to electronic ones. One of the main drawbacks is accuracy. While OCR software has made great strides, it still is not perfect. In most documents, there will be a few mistakes. Some scanners or All-In-Ones will come pre-packaged with a version of OCR software. This may provide basic features but typically is not a full version of the software; with a full version available for an additional charge.

OCR works by first scanning the chosen document using a scanner. This information is passed from the scanner to the computer and then from the computer to the OCR software. The Optical Character Recognition software processes the scanned image, attempts to recognize each individual character, and then save them in memory as a character, as opposed to a series of pixels in a scanned image. At this time OCR software is able to achieve over 95% accuracy. The only way to achieve complete accuracy is by manual review of the document.

Different printers and associated software have different methods to activate the OCR software. Some allow it during the scanning process while others require the use of dedicated OCR software. Check the included software and documentation of the printer to see if OCR software is included. Otherwise, visit your local Micro Center store to purchase OCR software.