Monday 29 January 2007

Digital do-gooder

My new-New Year's resolution / proof I'm really committed to my job: I'm going to become a volunteer proof-reader with Distributed Proofreaders, on online organisation set up to assist with the digitisation of books for Project Gutenberg.

One of the reasons I'm doing this - apart from the goodness of my heart - is that the digitisation of the books is being done using OCR (optical character recognition). We're running a project here at work using OCR to convert millions (well, million) of TIF files of pages of historical newspapers into fully text-searchable pages. I think/hope this will provide an interesting insight.

No comments: