>>>>> "Brad" == Brad Parker <brad_at_heeltoe.com> writes:
Brad> Hi,
Brad> If you had, say, 644 TIFF files, containing black and white
Brad> scanned text from a patent application. And say, you wanted to
Brad> turn that back into a text file, what would you do? The images
Brad> contain code listings.
Brad> Is a commercial OCR program the way to go? Any suggestions?
Brad> Is there any freely-available OCR which would be up to the
Brad> task?
Brad> (it's the Symbolics 3600 patent)
Adobe Acrobat (the full version, not the reader) has a downloadable
OCR option that's quite good. The free version can do 50 pages at a
time, so it takes a bit of work to do that many pages, but it can be
done. I've used it for a several hundred page document..
paul
Received on Sun Feb 15 2004 - 13:42:40 GMT
This archive was generated by hypermail 2.3.0
: Fri Oct 10 2014 - 23:36:42 BST