[ITK-users] Spatially variant morphological closing

[Daoued23]

Hi everyone,

I want to implement a spatially variant morphological closing, which its
structuring element is estimated for every pixel. I work on binary images.


So to apply the aspatially variant morphological closing, we estimate the
structuring element for every pixel surrounded by its neighborhood, apply
the dilation on every neighbouring window with the corresponding estimated
structring element. Then we get the dilated image as the union of all the
dilated windows. Now, we apply the erosion on every neighbouring window of
the dilated image with the transposed of the structuring element already
estimated. The adaptively closed image will be the union of the eroded
windows of the dilated image.

Now the problem is that, we find background windows (all pixels are black)
in the image, so we cannot estimate a structuring element. when it's the
phase of the dilation we don't apply anything, but some pixels can appear in
this windows as the result of the union of the surrounding windows that have
been dilated. When applying the erosion on these new pixels which
structuring element should we consider knowing that we can't estimate one
based on the original image (backgrounf window)???

Thank you

Best regards 



--
View this message in context: http://itk-users.7.n7.nabble.com/Spatially-variant-morphological-closing-tp36230.html
Sent from the ITK - Users mailing list archive at Nabble.com.