The use of paper has been displaced from some activities. For example, the vast majority of journeys on the London Underground are made using the Oyster card without a paper ticket being issued. We have witnessed talk of a paperless office for more than 40 years. However, the office environment has shown a resistance to remove the mountain of paper generated. Things have changed in the past few years, with a marked shift in the paperless office concept.
Paper documents contain a wealth of important management data and information that would be better stored electronically. There is computer software that makes this conversion possible. The benefit of scanning documents is not purely for archival reasons. OCR technology is vital for gaining access to paper-based information, as well as integrating that information in digital workflows.
The selection of the right OCR tool is dependent on specific needs. For some, online OCR services may be useful, but there are privacy concerns and file size limitations. This article focuses on desktop, open source OCR software that offer good recognition accuracy and support for a wide range of file formats. We cover OCR engines as well as front-end tools.