Hi -
I'm trying to put together a handwriting recognition system and am
looking for any advice that this group can offer.
I'm not interested in something simplistic like the restricted stroke
alphabet used in some PDAs. I'm aiming for something that can
recognize longhand cursive or shorthand, so this is rather ambitious.
I'm thinking of using something like tesseract's polygon approximation
scheme, except using splines because I'm matching strokes instead of
darkened regions. So my first idea is to come up with a linear or
quadratic spline approximation to a stroke and then use some kind of
matching algorithm (unclear exactly what algorithm) to match against a
database of reference strokes.
Any suggestions based on your experience with tesseract would be welcome.
Thank you.
-bwb
Brent Baccala
[email protected]
--
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To post to this group, send email to [email protected].
To unsubscribe from this group, send email to
[email protected].
For more options, visit this group at
http://groups.google.com/group/tesseract-ocr?hl=en.
