Classical Watershed 3D Algorithm
Pre-filters to apply before this algorithm
- Noise reduction filters (like median)
- Laplacian of Gaussian that can be found in Misc Filters 3D gives very good results
The Algorithm
Description:
- The watershed map is the maximum eigen value of the hessian transform (for details see featureJ page)
- The watershed is seeded with Regional Minima of the watershed map, in order to limit over-segmentation
- Propagation : propagation is done in the ascending order of the watershed map, starting from the seeds. It is a 3D 6-connectivity propagation.
- Propagation is done until a user defined global threshold is reached.
Over-segmentation
This algorithm can produce over-segmentation. This can be corrected with (at least) 2 operations:
- Reducing the noise during before computing the watershed map
- Using the post-filter Merge Regions
Post-filters
- As the propagation stops at a global threshold, a local threshold could be adjusted for each object. the post-filter Region Adjustment could be used.
- Classical morphological operations
Usage:
- Spots-like objects of small size like centromeres or genes