15 Aug
2006
15 Aug
'06
12:54 p.m.
On 8/15/2006 at 12:27 PM Don wrote:
> But what if you use mutiple OCR programs? Say,
three different OCR
> programs and then process the results taking a majority vote on each
> resulting character? Even if all three mangle 20%, it won't always be
the
> *same* 20% across all three, right? (and if I did
my math right, using
> three 80% accurate programs reduces the error rate to just 0.8% or a
> 99.2% accuracy rate)
OCR apps for music tend to range from miserable to truly dreadful. The
situation seems to be that if the best doesn't recognize something, neither
will the lesser programs. In my experience, using more than one program
doesn't improve things; it makes them worse.
I assume the originals are hand-drawn (though no doubt
on a
mechanically reproduced/ruled staff)?
Hand-drawn in the sense that the originals were either inked on manuscript
paper (i.e. pre-ruled) or hand-engraved.
For an interesting take on the complexity of engraving, the Lilypond
musical engraving program website has some examples of the nuances:
http://lilypond.org/web/about/automated-engraving/
Cheers,
Chuck