Optical character recognition (OCR) lets you turn scanned images into text so you can turn paper-based documents into editable, searchable, digital documents. This can help reduce the amount of physical space required to store documents and can dramatically improve workflows involving those documents. It reduces the risk of lost or misfiled documents and, in many cases, it eliminates the need to manually process documents or rekey information, which can result in errors. And it can reduce the costs of manual handling.
OCR analyses the patterns of light and dark that make up the letters and numbers to turn the scanned image into text. OCR systems need to recognise characters in various fonts, so rules are applied to help the system match what it sees in the picture to the right letters or numbers.
While early OCR systems were designed to work with one specific font, which was specially created for the purpose, some modern OCR systems can even recognise people’s handwriting. This technology is called intelligent character recognition (ICR).
For OCR to work optimally, it’s important that you scan the clearest possible version of the document. Blurred text or marks on the copy can create errors.
OCR programs recognise the text character by character but the outcome is so fast as to be instantaneous. You can check for errors as you go or at the end of the process, and some programs have automatic error detection.
Basic OCR technology has been around since the late 1920s. It’s become much more sophisticated since those early days and it can now convert even massively complex documents fast and with few errors. When documents are converted from their original format into the new format, they look exactly like the original with all formatting precisely replicated.
Request a quote
Konica will send you information on news, offers, and industry insights.