View Single Post
Old 12-02-2012, 05:12 PM   #13
SteveEisenberg
Grand Sorcerer
SteveEisenberg ought to be getting tired of karma fortunes by now.SteveEisenberg ought to be getting tired of karma fortunes by now.SteveEisenberg ought to be getting tired of karma fortunes by now.SteveEisenberg ought to be getting tired of karma fortunes by now.SteveEisenberg ought to be getting tired of karma fortunes by now.SteveEisenberg ought to be getting tired of karma fortunes by now.SteveEisenberg ought to be getting tired of karma fortunes by now.SteveEisenberg ought to be getting tired of karma fortunes by now.SteveEisenberg ought to be getting tired of karma fortunes by now.SteveEisenberg ought to be getting tired of karma fortunes by now.SteveEisenberg ought to be getting tired of karma fortunes by now.
 
Posts: 7,424
Karma: 43514536
Join Date: Jun 2008
Location: near Philadelphia USA
Device: Kindle Kids Edition, Fire HD 10 (11th generation)
Quote:
Originally Posted by automa View Post
Editing the spelling errors would be understandable because only humans can do that while the other two I mentioned probably can be automated via programming.
Here is a popular program used to pre-process optical character recognition long text output before proofreading:

http://home.comcast.net/~thundergnat/guiprep.html

As you can see from my link, an enormous amount of work has already gone into this.

You may have good ideas for additional features. However, it is was easy, or even middling difficult, I think it would already have been done. People are undoubtedly work on some of the hard stuff.

I'm not sure, but a lot of non-proofread texts at archive.org have perhaps already gone through this sort of software.
SteveEisenberg is offline   Reply With Quote