Equivalent of watershed for cutting connected components of an image of particles?

[Juan Nunez-Iglesias]

Hey Adam,




I'm *guessing* the IJ method is:

1. compute the thresholded background image (ie background labeled "True")

2. compute the Euclidean distance transform (scipy.ndimage.distance_transform_edt)

3. compute the local maxima (find_local_max) and set them as seeds

4. compute watershed, using the foreground as mask.




All of those functions are available in scipy/scikit-image. If you get good results, a gallery example of this would certainly be appreciated! =) However, my experience with such methods is that they only work well for reasonably sparse, perfectly spherical particles.




As to removing particles on the edge, I would use a bool mask with only the edges selected, then np.unique(), then remove them manually in a for loop. I agree that it's a bit laborious... Perhaps a separate function to do this could be added to the API...

On Thu, Feb 19, 2015 at 11:04 AM, Adam Hughes <hughesadam87 at gmail.com>
wrote:

> Hi,
> In ImageJ, one can select watershedding to break up connected regions of
> particles.  Are there any examples of using watershed in this capacity in
> scikit image?   All of the examples I see seem to use watershedding to do
> segmentation, not to break connected particles in an already-segmented
> black and white image.
> Also, is there a straightforward way to remove particles on a the edge of
> an image?  Sorry, googling is failing me, but I know this is possible.
> Thanks
> -- 
> You received this message because you are subscribed to the Google Groups "scikit-image" group.
> To unsubscribe from this group and stop receiving emails from it, send an email to scikit-image+unsubscribe at googlegroups.com.
> For more options, visit https://groups.google.com/d/optout.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.python.org/pipermail/scikit-image/attachments/20150218/31fb2dce/attachment.html>