I've been told the following three papers are the most relevant to
understanding the current algorithm (by the person who ported scribble to
Compaq's Virtual Book; this version of the code was eventually ported to
the Itsy and then Keith Packard added it to X (for Itsy and other
machines)):
X. Li and D. Y. Yeung, ``On-line handwritten alphanumeric character recognition
using dominant points in strokes'', Pattern Recognition, 30/1, 31-44 (1997)
X. Li and D. Y. Yeung, ``On-line handwritten alphanumeric character recognition
using feature sequences'', Proceedings of International Computer Science
Conference, 197-204 (1995)
X. Li and N. S. Hall, ``Corner detection and shape classification of on-line
handprinted Kanji strokes'', Pattern Recognition, 26/9, 1315-1334 (1993)
The first is the one that Carl Worth mentioned and the second is also
available at the same website he mentioned
(http://www.cs.ust.hk/faculty/dyyeung/paper/hr.html). The third one
doesn't sound particularly relevant to me, but I haven't read it myself.
I was poking around the files at Compaq, and we do have a version of the
trainer; unfortunately, it was last run approximately 5 years ago and it
needs quite a bit of work to get it running again. It sounds like the
version that Greg Haerr mentions is the best to start with at this point.
-Debby
Received on Thu Sep 7 11:18:41 2000
This archive was generated by hypermail 2.1.8 : Tue May 04 2004 - 09:42:16 EDT