[Optimoz] gesture recognition with a hidden markov model

[Aaron Lenfestey]

Hi guys,

I've been coding somewhat aggressively for the last couple days and am
rapidly approaching what will be the first iteration of a
recognization engine.  It is the more complex of the 2 models that I
already described.  Its written in C99 and uses nothing but standard
libraries.  Unfortunately, it will be difficult to gauge its
performance until we try it on some real world data, so I was hoping
one of you can help me construct the following data file which will
seed the model's estimates.

Specifically, the file must contain:

1) All valid output strings (sequences of characters from {U, L, R, D,
1, 3, 7, 9, *})

2) Probability estimates for each of these strings.  For now, these
don't need to be perfect, but we should try to make them reasonable. 
In the future, we can probably run a modified MozGest that logs
gestures, and then we can combine all the data to get empirical
estimates.

The function I've written to parse the data expects ASCII text, where
the first line is an integer that represents the total number of
strings in the dictionary.  Each subsequent line is of the form:

   <string_i> <space> <decimal_i> <newline>

i.e. recognized by scanf("%s %lf\n").  Where decimal_i is the prior
probability of the user gesturing string_i.  The function will
normalize the probabilities, so don't worry if they don't add up to 1.

-Aaron