Package gov.nih.mipav.model.algorithms

Class AlgorithmWatershed

java.lang.Object

java.lang.Thread

gov.nih.mipav.model.algorithms.AlgorithmBase

gov.nih.mipav.model.algorithms.AlgorithmWatershed

All Implemented Interfaces:

java.awt.event.ActionListener, java.awt.event.WindowListener, java.lang.Runnable, java.util.EventListener

public class AlgorithmWatershed
extends AlgorithmBase

This program applies the watershed algorithm to the image. It assumes that the user has identified the starting watershed regions via VOIs. Future work might be to develop a algorithm that automatically identifies initial seed points and regions or possibly an automatic method that forms watersheds - see method at end of file (does not work yet);

Version:

1.1 March 11, 1998

Author:

Matthew J. McAuliffe, Ph.D. and Ray Lert, MD

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
private class	AlgorithmWatershed.Seed	Simple class to hold seed point and basin (object label) value.

Nested classes/interfaces inherited from class java.lang.Thread

java.lang.Thread.State, java.lang.Thread.UncaughtExceptionHandler

Field Summary

Fields

Modifier and Type	Field	Description
private static short	BOUNDARY	DOCUMENT ME!
private ModelImage	energyImage	DOCUMENT ME!
private boolean	entireImage	If true, ignore VOIs and process entire image
private static short	INITIAL	DOCUMENT ME!
private static short	MASK	DOCUMENT ME!
private java.util.Vector<AlgorithmWatershed.Seed>	seedVector	DOCUMENT ME!
private float[]	sigmas	DOCUMENT ME!
private static short	WSHED	DOCUMENT ME!

Fields inherited from class gov.nih.mipav.model.algorithms.AlgorithmBase

destFlag, destImage, image25D, mask, maxProgressValue, minProgressValue, multiThreadingEnabled, nthreads, progress, progressModulus, progressStep, runningInSeparateThread, separable, srcImage, threadStopped

Fields inherited from class java.lang.Thread

MAX_PRIORITY, MIN_PRIORITY, NORM_PRIORITY

Constructor Summary

Constructors

Constructor	Description
AlgorithmWatershed(ModelImage destImg, ModelImage srcImg, ModelImage gmImg, float[] sigmas, java.util.Vector<AlgorithmWatershed.Seed> seeds)	Constructs new watershed algorithm.
AlgorithmWatershed(ModelImage destImg, ModelImage srcImg, ModelImage gmImg, float[] sigmas, java.util.Vector<AlgorithmWatershed.Seed> seeds, boolean entireImage)	Constructs new watershed algorithm.

Method Summary

Modifier and Type	Method	Description
private void	calc2D()	Calculates the watershed intialized by the VOI regions.
private void	calc3D()	Calculates the watershed intialized by the VOI regions.
void	finalize()	Prepares this class for destruction.
void	runAlgorithm()	Starts the program.
void	setEnergyImage(ModelImage _energyImage)	This image is typically the gradient magnitude.
void	setSeedVector(WildMagic.LibFoundation.Mathematics.Vector3f[] seedPoints)	Sets the seed vector.

Methods inherited from class gov.nih.mipav.model.algorithms.AlgorithmBase

actionPerformed, addListener, addProgressChangeListener, calculateImageSize, calculatePrincipleAxis, computeElapsedTime, computeElapsedTime, convertIntoFloat, delinkProgressToAlgorithm, delinkProgressToAlgorithmMulti, displayError, errorCleanUp, fireProgressStateChanged, fireProgressStateChanged, fireProgressStateChanged, fireProgressStateChanged, fireProgressStateChanged, generateProgressValues, getDestImage, getElapsedTime, getMask, getMaxProgressValue, getMinProgressValue, getNumberOfThreads, getProgress, getProgressChangeListener, getProgressChangeListeners, getProgressModulus, getProgressStep, getProgressValues, getSrcImage, isCompleted, isImage25D, isMultiThreadingEnabled, isRunningInSeparateThread, isThreadStopped, linkProgressToAlgorithm, linkProgressToAlgorithm, makeProgress, notifyListeners, removeListener, removeProgressChangeListener, run, setCompleted, setImage25D, setMask, setMaxProgressValue, setMinProgressValue, setMultiThreadingEnabled, setNumberOfThreads, setProgress, setProgressModulus, setProgressStep, setProgressValues, setProgressValues, setRunningInSeparateThread, setSrcImage, setStartTime, setThreadStopped, startMethod, windowActivated, windowClosed, windowClosing, windowDeactivated, windowDeiconified, windowIconified, windowOpened

Methods inherited from class java.lang.Thread

activeCount, checkAccess, clone, countStackFrames, currentThread, dumpStack, enumerate, getAllStackTraces, getContextClassLoader, getDefaultUncaughtExceptionHandler, getId, getName, getPriority, getStackTrace, getState, getThreadGroup, getUncaughtExceptionHandler, holdsLock, interrupt, interrupted, isAlive, isDaemon, isInterrupted, join, join, join, onSpinWait, resume, setContextClassLoader, setDaemon, setDefaultUncaughtExceptionHandler, setName, setPriority, setUncaughtExceptionHandler, sleep, sleep, start, stop, suspend, toString, yield

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, wait, wait, wait

Field Detail

BOUNDARY

private static final short BOUNDARY

DOCUMENT ME!

See Also:

Constant Field Values

MASK

private static final short MASK

DOCUMENT ME!

See Also:

Constant Field Values

INITIAL

private static final short INITIAL

DOCUMENT ME!

See Also:

Constant Field Values

WSHED

private static final short WSHED

DOCUMENT ME!

See Also:

Constant Field Values

energyImage

private ModelImage energyImage

DOCUMENT ME!

seedVector

private java.util.Vector<AlgorithmWatershed.Seed> seedVector

DOCUMENT ME!

sigmas

private float[] sigmas

DOCUMENT ME!

entireImage

private boolean entireImage

If true, ignore VOIs and process entire image

Constructor Detail

AlgorithmWatershed

public AlgorithmWatershed(ModelImage destImg,
                          ModelImage srcImg,
                          ModelImage gmImg,
                          float[] sigmas,
                          java.util.Vector<AlgorithmWatershed.Seed> seeds)

Constructs new watershed algorithm.

Parameters:

destImg - Image model where result image is to stored

srcImg - Source image model

gmImg - Gradient magnitude image (can be null)

sigmas - Gaussian's standard deviations in the each dimension

seeds - Seed points for starting watershed

AlgorithmWatershed

public AlgorithmWatershed(ModelImage destImg,
                          ModelImage srcImg,
                          ModelImage gmImg,
                          float[] sigmas,
                          java.util.Vector<AlgorithmWatershed.Seed> seeds,
                          boolean entireImage)

Constructs new watershed algorithm.

Parameters:

destImg - Image model where result image is to stored

srcImg - Source image model

gmImg - Gradient magnitude image (can be null)

sigmas - Gaussian's standard deviations in the each dimension

seeds - Seed points for starting watershed

entireImage - If true, ignore VOIs and process entire image

Method Detail

finalize

public void finalize()

Prepares this class for destruction.

Overrides:

finalize in class AlgorithmBase

runAlgorithm

public void runAlgorithm()

Starts the program.

Specified by:

runAlgorithm in class AlgorithmBase

setEnergyImage

public void setEnergyImage(ModelImage _energyImage)

This image is typically the gradient magnitude. Peaks in this image (function ) are the watersheds boundaries

Parameters:

_energyImage - the energy image (function)

setSeedVector

public void setSeedVector(WildMagic.LibFoundation.Mathematics.Vector3f[] seedPoints)

Sets the seed vector.

Parameters:

seedPoints - The seed points.

calc2D

private void calc2D()

Calculates the watershed intialized by the VOI regions. The resultant watershed regions(basin) are labelled with an integer value. In addition, each region is separated by connected (8-way) watershed identifier of 1.

calc3D

private void calc3D()

Calculates the watershed intialized by the VOI regions. The resultant watershed regions(basin) are labelled with an integer value. In addition, each region is separated by connected (8-way) watershed identifier of 1.