Hi,

I'm using the Exact Large-Scale Mean-Shift segmentation framework to 
successfully segment my images. As an output I get the raster with regions 
and the shapefile which contains an attribute table with some radiometric 
attributes. I am looking for the most efficient way to also get the shape 
attributes from my segmented image. 
Is there a build-in function to compute the shape attributes which are also 
available through itkShapeLabelObject 
(https://itk.org/Doxygen/html/itkShapeLabelObject_8h_source.html)? I know 
that when using the CC segmentation it is possible to use these attributes 
as an OBIA expression with the following syntax: 'SHAPE_Elongation, 
SHAPE_perimeter etc..'. I would like to have these attributes either in the 
shapefile or as an raster attribute table. 

Also, is it possible to get information on texture (smoothness, local 
homogeneity) and relation to neighbors, subobjects and superobjects using 
one of the Orfeo tools? Other Python libraries are also welcome! I am now 
using regionprops from the skimage library to compute shape attributes. 

Many thanks in advance.

Kind regards,
Darell

-- 
-- 
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