Yes, thank you, Carol! To clarify: The documents are English language with mostly simple fonts. There is some handwritten text in the more recent issues of this publication, but we're working from the 1940's forward, so we can come up with another solution for the handwriten stuff down the line, I think. We primarily need to get this off the ground first to prove the concept locally.
On Mon, Apr 18, 2016 at 10:56 AM, Carol Kassel <[email protected]> wrote: > Hi Rachel, > > I assume you're talking about OCR for English language texts with simple > fonts. :-) > > If so, we've been using Tesseract with good results. It's open source. > > Good luck! > > Best wishes, > > Carol > > On Mon, Apr 18, 2016 at 10:51 AM, Rachel Gravel <[email protected]> > wrote: > > > Greetings, > > > > Might anyone have some recommendations on good OCR software that is > either > > relatively cheap or free? We're looking to OCR some files for a digital > > collection (platform still to be determined...) and wonder if there's a > > more robust tool than Acrobat Pro that won't cost an arm and a leg. > > > > Many thanks in advance for your expertise! > > > > Cheers, > > Rachel > > > > -- > > [email protected] > > (617)870-4179 > > www.linkedin.com/pub/rachel-gravel/4/318/908 > > > > > > -- > Carol Kassel > Senior Manager, Digital Library Infrastructure > NYU Digital Library Technology Services > [email protected] > (212) 992-9246 > dlib.nyu.edu > -- [email protected] (617)870-4179 www.linkedin.com/pub/rachel-gravel/4/318/908
