Hello,

I'm using otbcli_TrainImagesClassifier to classify images. Right now I'm 
creating classifiers, and it's working fine on multiple images, but then I 
came across one where the classifier produced a label that was not in the 
training data set.  The classification matrix is: 

#Reference labels (rows):70,200
#Produced labels (columns):20,70,200
2626,17083,2857
54632,24413,59378


Why would it produce a label that was not in the reference set?  And why in 
such abundance? 

This is the command that I called: 

call otbcli_TrainImagesClassifier -io.il Imagery/2010/P3_10cm1.tif  -io.vd 
"ImageAnalysis/TrainingShapefiles/Train3_many.shp"   -io.imstat 
ImageAnalysis/2010Stats/Stats3.xml  -sample.mv 100 -sample.mt 100 
-sample.vtr 0.5 -sample.edg false -sample.vfn Class10 -classifier libsvm 
-classifier.libsvm.k linear -classifier.libsvm.c 1 -classifier.libsvm.opt 
false -io.out "ImageAnalysis/Classifiers/2010Plot3many.svm" -io.confmatout 
"ImageAnalysis/ConMats/2010Plot3many.conmat"

Thank you for any insight!

-- 
-- 
Check the OTB FAQ at
http://www.orfeo-toolbox.org/FAQ.html

You received this message because you are subscribed to the Google
Groups "otb-users" group.
To post to this group, send email to [email protected]
To unsubscribe from this group, send email to
[email protected]
For more options, visit this group at
http://groups.google.com/group/otb-users?hl=en
--- 
You received this message because you are subscribed to the Google Groups 
"otb-users" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].
For more options, visit https://groups.google.com/d/optout.

Reply via email to