I have been completely unable to find details on the underlying model that is used for the Palm Pilot Graffiti handwriting recognition. Given the computing power available for handheld PDA technology, I have always been quite surprised this was possible at that time. I was hoping for a source with information about the model, e.g., features, recognition method, etc.
If you are looking for a good explanation of some of the methods used in projects like GRAIL look here:
It seems most of the data is in Graffiti (Palm OS) - Wikipedia.
It seems the technology is related to Unistrokes technology (U.S. Patent 5,596,656, granted in 1997).
Since the model relies on single stroke and using symbols that are exceptionally well separated from each other graphically I would be assume parameterizing the stroke would be a great way to get well separated features. Just the coordinate and the relation between them will be perfect.
if you can get into the IEEE Explore Library
D. J. Burr, "Designing a Handwriting Reader," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-5, no. 5, pp. 554-559, Sept. 1983.
and then look at the citations, which include both the Palm and Xerox Patents. Xerox claimed that Palm infringed so you might pick up some clues.