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
signature.asc
Description: This is a digitally signed message part.
_______________________________________________ grass-user mailing list [email protected] http://lists.osgeo.org/mailman/listinfo/grass-user
