James Fraser (wheresthatistanbul-newtontalk@yahoo.com) wrote:
> Is there a known reason why the "Learn" capability wasn't paired with
> printed writing as it is with cursive?
>
> Were there hardware/software considerations? Or did Apple simply feel
> that the print recognizer was "good enough" as it was and that most
> users would employ cursive writing anyway?
For one thing, Apple had licensed Paragraph's cursive recognizer "as
is", and it happened to be able to learn from mistakes. The print
recognizer, on the other hand, was an in-house development.
As to the reasons why it doesn't learn, Larry Yaeger had explained those
in May last year:
"The print recognizer does not learn. It does adjust its expectations
about character height, so it might get a tiny bit better about case
disambiguation if you are consistent over time. But other than that, a
learning version was never deployed. (It's based on a neural network,
so it certainly could learn, and does learn the user-independent
behavior prior to shipping; that technology was just never put into the
shipping product.)"
Btw, in my experience the print recognizer wasn't just "good enough", it
was better than the cursive recognizer. For my own handwriting anyway.
After having upgraded my MP 120 to NOS 2.0 (the first version of the OS
to include the print recognizer), the recognition rate went up sharply.
- Michael
Michael J. Hußmann
E-mail: michael@michael-hussmann.de
WWW (personal): http://michael-hussmann.de
WWW (professional): http://digicam-experts.de
====================================================================
The NewtonTalk Mailing List - http://www.newtontalk.net/
The Official Newton FAQ - http://www.splorp.com/newton/faq/
The Newton Glossary - http://www.splorp.com/newton/glossary/
WikiWikiNewt - http://tools.unna.org/wikiwikinewt/
====================================================================
Received on Sat Jan 10 19:31:30 2009
This archive was generated by hypermail 2.1.8 : Sat Jan 10 2009 - 23:30:01 EST