Gillard Editing provides an OCR (optical character recognition) service to extract text from documents which have a clearly recognisable typeface. Advanced “training” techniques bring a better level of text recognition than offered by off-the-shelf programs; this allows physical archives to be converted into searchable digital resources.

Our image-to-text bureau service is by far the UK’s fastest, largest and most accurate and operates at up to ten times the speed of any other domestic OCR provider.

The Hound of the Baskervilles …and after: OCR facsimile of The Hound of the Baskervilles

The Hound of the Baskervilles by Sir Arthur Conan Doyle, Strand Magazine 1901. The left-hand image shows a low-resolution unsearchable scan, whereas the right-hand image shows the resulting fully searchable pdf facsimile. The OCR process makes it possible to search for terms contained within a particular page, within a complete multi-page document, or across an entire collection of documents. Click on the images to see the full-sized versions.

German gothic script

Conversion of German gothic “Fraktur” script into text-searchable pdf format, enabling analysis of difficult documents.

The various centenaries associated with World War One have created a huge interest in such material, and Gillard Editing is the only UK-based provider able to automate the interpretation of Fraktur on such a scale.

Fraktur Output: Fraktur output

Gillard Editing is an Abbyy partner company.

© Gillard Editing
Kent, UK

Designed by Gillard Editing

Valid XHTML 1.0 Valid CSS