Module: Separate Objects / Chamfer - Conservative ()
This module computes the watershed lines of a binary image. You can adjust the contrast level which is used to reduce the number of markers for the watershed process.
This module is a high-level combination of watershed, distance transform and numerical reconstruction algorithms. There is a limitation to the separating ability: if some particles overlap too much, they will not be separated. This module can be used on the gradient modulus to compute best-fit contours.
See also: H-Extrema Watershed.
Input Binary Image [required]
The image to be processed. Supported types are: binary images (Uniform Label Field with 2 labels).
Type
This port selects the configuration of this module.Interpretation
This port specifies whether the input will be interpreted as a 3D volume or a stack of 2D images for processing.
- "3D": the module configuration is set to 3D. The image will be processed as a whole in 3D.
- "XY planes": the module configuration is set to 2D. The image will be processed slice per slice.
Neighborhood
In 3D configuration, this port refers to the type of connectivity considered for processing adjacent voxels:
- 6: voxels with a common face are considered connected
- 18: voxels with at least one common edge are considered connected
- 26: voxels with at least one common vertex are considered connected
Marker Extent
This port specifies a number used as a contrast factor to reduce the number of seeds for the watershed. Higher values increase the number of merged seeds, therefore reduce the final number of remaining seeds. It has the same meaning as the contrast factor of H-Maxima.Output Type
This port selects the content of the output image. It is one of the following:
split: Original data minus separation lines (split particles)
line: Separation lines
basins: Watersheds
basins2: Watersheds without separation lines
connected object: Watersheds without separation lines masked by the binary input image
Algorithm Mode
This port selects the type of algorithm used to separate the objects. It is one of the following:
repeatable: repeatable but slower
fast: faster but not repeatable because of asynchronous parallel computation.