[tug-summer-of-code] [Fwd: Re: A couple of project proposals]

[Scott Pakin]

Jonathan Fine wrote:
> I'm fairly confident the project will be able to produce something
> useful, based on the 'conceptual' metadata.  I have no such confidence
> for the handwriting recognition approach.

Remember, though, that unlike the typical handwriting-recognition
problem,

   1) we need to recognize only a single character at a time (more like
      Kanji than Latin, I suppose), so there's no need to detect where
      one character ends and the next begins, and

   2) we don't need to return a single correct answer but rather a set
      of the top N most likely candidates.

> Here's a link to what may be the state of the art.
>     http://www.orcca.on.ca/PenMath/demos.html
> 
> You might also want to look at
>    http://www.orcca.on.ca/MathML/NotationSelectionTool/
> 
> http://imps.mcmaster.ca/na-mkm-2004/proceedings/pdfs/smirnova-abstract.pdf
> http://imps.mcmaster.ca/na-mkm-2004/proceedings/pdfs/smirnova-presentation.pdf 
>
> Here's the search I used.
>    http://www.google.com/search?q=mathematics+handwriting+recognition

Thanks for the links.  Checking them out...

> I suggest we consult some of these people, and ask for their opinion.

Sounds reasonable.  Or should we have the student do that (at stage 0
of the project -- as we're negotiating the proposal)?

-- Scott