Bill Hudspeth:
 
> I am trying to build a signature file for a three band NAIP image (digital
> orthophotography....red, blue, green) using i.cluster. I am largely
> accepting the defaults to begin with (classes=10, iterations=30,
> convergence=98, separation=0), but have tried a separation of 0.5 and 1.0.
> In all cases I get 100% convergence with only one cluster generated. Any
> ideas on what might be going on??

Just wild guessing:

# checking resolution and extent
g.region -p

# does the group include all three channels?
i.group naip_rgb -l

Best, Nikos

Attachment: signature.asc
Description: This is a digitally signed message part.

_______________________________________________
grass-user mailing list
[email protected]
http://lists.osgeo.org/mailman/listinfo/grass-user

Reply via email to