Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

marker controlled Watershed #17

Open
haesleinhuepf opened this issue Sep 24, 2020 · 4 comments
Open

marker controlled Watershed #17

haesleinhuepf opened this issue Sep 24, 2020 · 4 comments
Labels
enhancement New feature or request

Comments

@haesleinhuepf
Copy link
Member

Suggested by @pr4deepr

'''
Marker controlled watershed from MorpholibJ
If I am using CLIJx to generate seeds (labelling) and binary images (mask), then if I have edges image I can use these images for segmenting cells using Marker Controlled Watershed.
'''

See also:
https://github.com/clij/assistant/issues/14
@haesleinhuepf
Copy link
Member Author

Hey @pr4deepr ,

have you tried
https://clij.github.io/clij2-docs/reference_seededWatershed

?

Thanks!

@haesleinhuepf haesleinhuepf mentioned this issue Sep 24, 2020
Closed
@haesleinhuepf haesleinhuepf added enhancement New feature or request help wanted Extra attention is needed and removed help wanted Extra attention is needed labels Sep 24, 2020
@haesleinhuepf haesleinhuepf changed the title wishlist: marker controlled Watershed marker controlled Watershed Sep 24, 2020
@pr4deepr
Copy link
Contributor

I just tried it.

  • Top row is seeded watershed: The input image from CLIJx assistant, followed by labelling workflow ALX and then seeded watershed in CLIJx.
  • Bottom row is marker controlled watershed: the edges image (Canny-Deriche) and binary image with same threshold specified as in CLIJx assistant. The final labelled image is on the right.

The labelling wasn't optimised as much, but this demonstrates the differences.

image

@haesleinhuepf
Copy link
Member Author

Awesome! I can see the issue now. Does it also fail in 2D? Can you share the dataset and the script which generates both results? That would make it easy for me to trace it down in more detail.

@pr4deepr
Copy link
Contributor

I haven't tried 2D.

Yup, happy to share the dataset.
Both the image and the macro is in this folder.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@haesleinhuepf @pr4deepr