SoMarkerBasedWatershedProcessing Class Reference
[Region Growing]

ImageViz SoMarkerBasedWatershedProcessing engine performs a fast determination of the watershed lines. More...

#include <ImageViz/Engines/ImageSegmentation/RegionGrowing/SoMarkerBasedWatershedProcessing.h>

Inheritance diagram for SoMarkerBasedWatershedProcessing:
SoImageVizEngine SoEngine SoFieldContainer SoBase SoRefCounter SoTypedObject

List of all members.

Public Types

enum  OutputMode {
  SEPARATED_BASINS = 0,
  WATERSHED_RIDGES = 1
}
enum  PrecisionMode {
  REPEATABLE = 0,
  FAST = 1
}

Public Member Functions

 SoMarkerBasedWatershedProcessing ()

Public Attributes

SoSFEnum computeMode
SoSFEnum neighborhood3d
SoSFEnum outputMode
SoSFImageDataAdapter inGrayImage
SoSFImageDataAdapter inMarkerImage
SoSFEnum precisionMode
SoImageVizEngineOutput
< SoSFImageDataAdapter,
SoImageDataAdapter * > 
outObjectImage

Detailed Description

ImageViz SoMarkerBasedWatershedProcessing engine performs a fast determination of the watershed lines.

For an introduction, see Watershed principle.

SoMarkerBasedWatershedProcessing has 2 configurations. See outputMode field.

This engine performs a fast determination of the watershed lines from specified markers in a label image, followed by a labelling of the complementary set. It can be viewed as the zones of influence of the markers.

Either the separated basins are output in a label image, the crest lines being part of the complementary (not a label), or the crest lines are output in a binary image.

Note: Because two bits are used to code the pixels during the algorithm, input gray levels image should range from 0 to 16383. If the range is greater, a normalization is applied to reduce the dynamic of this image.

SoMarkerBasedWatershed_image01.png

Example of SoMarkerBasedWatershedProcessing engine with SEPARATED_BASINS mode

Notice: This engine requires to preliminarily load the whole input data set into memory to be computed. As a consequence the input data set will be automatically loaded before the execution of this engine, ignoring the maximum memory parameter of the SbImageDataAdapterHelper::getAppropriateAdapter function or SoFileDataAdapter class

If the input data set cannot fit in memory, this engine will fail during its computation.

SEE ALSO

SoAddObjectToLabelProcessing, SoGrayscaleResconstructionProcessing

FILE FORMAT/DEFAULT


Library references: catchbasin fastwatershed

See related examples:

MarkerPicking, PoreAnalysis, MedicalSegmentation


Member Enumeration Documentation

Enumerator:
SEPARATED_BASINS 

The separated basins are output in a label image, the crest lines being part of the complementary (not a label).

WATERSHED_RIDGES 

The crest lines are output in a binary image.

Enumerator:
REPEATABLE 

Default mode, produce unique results.

FAST 

Algorithm use parallelism (if allowed) during inundation step.

Since fast watershed problem has generally not a unique solution, two processes of same image can lead to two different results (both exact).


Constructor & Destructor Documentation

SoMarkerBasedWatershedProcessing::SoMarkerBasedWatershedProcessing (  ) 

Constructor.


Member Data Documentation

Select the compute Mode (2D or 3D or AUTO) Use enum ComputeMode.

Default is MODE_AUTO

The input grayscale image.

Default value is NULL. Supported types include: grayscale image.

The input marker (label) image.

Default value is NULL. Supported types include: label color image.

In 3D configuration (see computeMode), the neighborhood connectivity defines the connectivity considered for processing adjacent voxels.

Use enum Neighborhood3d. Default is CONNECTIVITY_26.

The output image.

Default value is NULL. Supported types include: binary image.

Select the type of output mode.

Use enum OutputMode. Default is WATERSHED_RIDGES

Select the mode of algorithm precision for watershed.

Use enum PrecisionMode. Default is REPEATABLE


The documentation for this class was generated from the following file:

Open Inventor Toolkit reference manual, generated on 15 Mar 2023
Copyright © Thermo Fisher Scientific All rights reserved.
http://www.openinventor.com/