[GRASS-dev] i.smap code only for segmentation, not classification

[Moritz Lennert]

Hello,

Does anyone how difficult it would be to modify i.smap or reuse some of 
its code to only do image segmentation, without classification and 
without prior identification of training zone signatures ?

I am asking this since colleagues are currently busy benchmarking 
segmentation algorithms and I thought it might be interesting to see how 
the algorithm in i.smap would do...

Moritz