Using handwritten text recognition software

The National Archives has been running a pilot project to test out the feasibility of using a type of handwritten text recognition (HTR) software.

You may be familiar with OCR – the technology that enables us to search the words written inside a book, newspaper or archival document. It’s what’s behind The Gazette search. However, OCR doesn’t work on documents that are handwritten.

The new platform, called Transkribus, developed by the EU funded READ Project, offers the potential to use computers to do just that, for the very first time.

The National Archives is focusing on the PROB 11 wills collection, due to its uniform handwriting style and structured language patterns.

Read more about The National Archives' continuing work with HTR: The National Archives blog