Submission + - Academic applications of OCR 4
kg1794 writes: "In my recent PhD research, I've been looking at a 1,200 page typed but unpublished manuscript from a (unfortunately now deceased) political science professor. The end goal is to eventually bring this work to publication, but I don't have the original file he created this manuscript with (it was completed back in 1979). The document needs a degree of editing and re-arranging, but what's the best way of getting these pages into digital form that doesn't involve typing the whole lot out? How and who can do such a large scale OCR task for a nominal (read: university humanities research grant) fee? How feasible is a home-brew system with some kind of auto-document feeder? Any academics or researchers who have digitized source collections in the past would be very welcome to assist. I'm in the UK, but understand solutions for this may be more efficient from across the pond. Thanks."