Just wondering if anyone out there involved with digitization of modern
printed material is aware of any independent studies of accuracy rates
comparing rekeying workflows (double/"triple" rekeying) versus OCR-based
methods.

Conversion vendors are increasingly claiming that advances in OCR
technology (both hardware and error-correction heuristics) are moving
accuracy rates into the range traditionally associated with
double-keyboarding workflows (>99.995%). Whether that's true is another
matter. Since in either case vendor digitization relies on various
proprietary combinations of human tasks + hardware + software, it's not
obvious how one would do an independent study with reproducible results.

Are such studies out there? I'll settle for anecdotal wisdom if they're
not.

DS

-- 
David Sewell, Editorial and Technical Manager
ROTUNDA, The University of Virginia Press
PO Box 801079, Charlottesville, VA 22904-4318 USA
Courier: 310 Old Ivy Way, Suite 302, Charlottesville VA 22903
Email: [log in to unmask]   Tel: +1 434 924 9973
Web: http://rotunda.upress.virginia.edu/