There are some settings in Kurzweil 1000 that makes a difference in the accuracy of OCR. We are currently experiment and documenting how changing those settings will affect the OCR accuracy. Kathy Konicek >Hello, > >I've used Kurzweil 1000 to recognize a few PDF documents, though none that >were image based. It worked well. The only problem was that, as with any >OCR, there were recognition errors. But this does seem to be a viable way >of accessing PDF documents. > >Regards, >Anna