From http://lists.okfn.org/pipermail/okfn-discuss/2007-November/005868.html:

Working with the Shakespeare entry from 11th edition of the Encyclopaedia Britannica over the last year, and particularly the experience of using tesseract, has got me thinking about a couple of potential projects along the same lines:

1. OCRing all of the EB 11th edition and putting it up online. If we put this in something that was editable this might also be a quicker way to do the proofing than the pgdp approach (which is currently working on some of the earlier volumes but is proceeding fairly slowly). It is interesting that some people have done this kind of thing already (see examples at the end of the Wikipedia article on the EB 11th edition [1]) but all of them seem to be closed (i.e. claim copyright on the results).

Steps Required

1. OCR existing scanned text (on wikimedia commons)
2. Put online in editable format for proofing/correction