Hausdorff distance-based matching code available.

[William Rucklidge <wjr@cs.cornell.edu>]

The source code to the Hausdorff distance model-based recognition code
that Dan Huttenlocher and I (and others) have developed is now
available. It is in ftp.cs.cornell.edu:pub/wjr/Hausdorff.tar.gz
(you'll need GNU zip to uncompress it). This system performs matching
based on binary images, typically dense images like Canny edges,
quickly and reliably.

This code implements the systems described in
D.P. Huttenlocher, G.A. Klanderman, and W.J. Rucklidge,
"Comparing images using the Hausdorff distance.", IEEE Transactions on
Pattern Analysis and Machine Intelligence, 15(9):850-863, September 1993.

and

D.P. Huttenlocher and W.J. Rucklidge,
"A multi-resolution technique for comparing images using the Hausdorff
distance", Proc. Computer Vision and Pattern Recognition, pages 705-706,
1993.

and in my Ph.D. thesis, "Efficient Computation of the Minimum Hausdorff
Distance for Visual Recognition", Cornell University. This thesis will soon
be available as a Technical Report from the Department of Computer Science,
Cornell University; see the URL http://cs-tr.cs.cornell.edu/ for
information about how to get the TR via the Web.


William Rucklidge			wjr@cs.cornell.edu
"You know, you can save a lot off your power bill by just taping a Budget
 Gourmet dinner to the side of the computer monitor" - Mike Jittlov

------------------------------