next up previous index
Next: ``Marker-based_WS_relax'' - segment an Up: Segmentation Previous: ``Cue-based_watershed'' - segment an

``Cue-based_WS_relax'' - segment an image using watershed relaxation using cues

VFX name:
iCueWshedRelax
IMPROMPTU Equivalent:
Cue-based_watershed_relax
purpose:
Watershed Relaxation uses both Watershed analysis [#EO93 and Relaxation labeling [#HA93a<#1907##1###,###1###,##speed of watershed analysis and region smoothing property of relaxation labeling to produce a better segmented output when compared to watershed analysis alone.
input:
Two 8-bit volumes ( original image and gradient image).
output:
An 8-bit volume in segmentation volume format (refer to the demask region<#1910##1###,##p. [*]) containing the segmented regions .
parameters:
Default parameters menu is
grad_vol = 0
cue_filename = foobar
num_regions = 2
num_iter = 10
percent_neigh = 25.0
exclude_cues = no
final_seg_thresh = 0.0
If the final segmentation threshold is set to 0.0, then the maximum vector component for each voxel is assumed to represent that voxel's appropriate labeling. If a threshold is set, then the maximum vector component value for a voxel must be greater than the threshold value for that voxel to be labeled as part of a region.
comments:
See below.
1.
See Marker-based_WS_relax for a comparable function.


next up previous index
Next: ``Marker-based_WS_relax'' - segment an Up: Segmentation Previous: ``Cue-based_watershed'' - segment an
MultiDimensional Image Processing Lab, Penn State University