> I am interested in the subject of Snakes, and I would appreciated if
> you, or anyone else, can point to few basic references to start with.
> Do you know a site where someone can FTP "Snakes" (if it is available)?
> Is your program is dependable? Are you willing to share it with others?
> Thank you ...
Well, the references I have are:
Michael Kass, Andrew Witkin, Demetri Terzopoulos, "Snakes: Active Contour
Models", Int. J. Computer Vision, 1, 1987, pp 321-331.
(The original paper)
Laurent D. Cohen, "On Active Contour Models and Ballons", CVGIP: Image
Understanding, Vol. 53, No. 2, March 1991, pp 211-218.
(Introduces extensions and improvements on the original model)
Amir Amini, Terry Weymouth, Ramesh Jain, "Using Dynamic Programming for
Solving Variational Problems in Vision", IEEE Trans. on Pattern Analysis
and Machine Intelligence, Vol. 12, No. 9, September 1990, pp 855-867.
(Makes a comparison between Snakes and Dynamic Programming for Edge
Donna Williams, Mubarak Shah, ""A Fast Algorithm for Active Contours and
Curvature Estimation", CVGIP: Image Understanding, Vol. 55, No. 1,
January 1992, pp 14-26.
(More improvements on the Snake algorithm)
The implementation I have is coded in C++ (compiled with g++ v 2.5.8, don't
know about cfront) and uses IRIS GL for graphics interaction. So my guess is
it should work properly on any SGI platform running IRIX 4.0.5F. Since
IRIX 5.0.x has moved on to OpenGL some rewrites are needed here. I never
tried it on any other platform. I will gladly mail it to you but if more
people are interested I will make it available trough anonymous ftp.
I decided to drop the semi-implicit ODE solver used by Kass et al in their
paper since I wanted high refresh rates so a simple Euler method was
used. As a result the snake tends to oscillate a little and the edge
determination loses accuracy but I get real time interaction.