Re: [computer-go] finding groups as an image segmentation problem

[Markus Enzenberger <compgo@xxxxxxxxxxxxxxxxxxxxx>]

On Sunday 11 January 2004 12:21, Robin Kramer wrote:
> the idea being that one would construct an affinity matrix that is
> 361X361, each element in the matrix would represent how much affinity
> each position had to each other position.

NeuroGo does something like that in its latest version, see
http://www.markus-enzenberger.de/neurogo.html
It is not directly related to image segmentation algorithms used elsewhere.

- Markus

_______________________________________________
computer-go mailing list
computer-go@xxxxxxxxxxxxxxxxx
http://computer-go.org/mailman/listinfo/computer-go