Package gov.nih.mipav.model.algorithms

Class AlgorithmHistogram

java.lang.Object

java.lang.Thread

gov.nih.mipav.model.algorithms.AlgorithmBase

gov.nih.mipav.model.algorithms.AlgorithmHistogram

All Implemented Interfaces:

ActionListener, WindowListener, Runnable, EventListener

public class AlgorithmHistogram
extends AlgorithmBase

Calculates the histogram for an image. The number of bins is determined by the extents of the histogram model. The calling algorithm can specify if the histogram is to be calculated for whole image or only over VOI regions. The Otsu and Maximum Entrophy thresholds are also automatically calculated and stored in the ModelHistogram structure. The Otsu and Max entropy can take time (minutes) to calculate for histgrams with bins larger than (10,000).

Version:

0.1 September 18, 1997

See Also:

• ModelHistogram

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
private class	AlgorithmHistogram.GrayLevelClass	Used specifally by the Otsu threshold algorithm to define a gray level object for calculating probabilities.

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

Thread.Builder, Thread.State, Thread.UncaughtExceptionHandler

Field Summary

Fields

Modifier and Type	Field	Description
private boolean	dataOutput	Flag indicating whether or not histogram data is output to the data window.
private boolean	displayGraph
private boolean	entireImage	If true the histogram should be calculated for the entire image.
private double[]	highValue	DOCUMENT ME!
private int[]	histoBuffer	DOCUMENT ME!
private ModelHistogram	histogram	Reference to the histogram storage object.
private ModelImage	image	Reference to the image.
private double[]	lowValue	DOCUMENT ME!
private int	processMode
private int	RGBOffset	Indicates which channel of the RGB image the histogram should be calculated. 1 = Red channel 2 = Green channel 3 = Blue channel
private static final int	SEPARATE_VOIS
private int	summaryBins	Used to indicate the number of histogram bins when using the constructors that do NOT pass in the histogram object.
private static final int	TOTAL_VOIS
private boolean	userLimits
private double	userMax
private double	userMin
private static final int	WHOLE_IMAGE

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
AlgorithmHistogram(ModelHistogram histogram, int RGBOffset, ModelImage image, boolean maskFlag)	Constructs the histogram calculation object for an RGB image.
AlgorithmHistogram(ModelHistogram histogram, ModelImage image, boolean maskFlag)	Constructs the histogram calculation object.
AlgorithmHistogram(ModelImage image, int summaryBins)	Constructs the histogram calculation object for an image.
AlgorithmHistogram(ModelImage image, int summaryBins, boolean maskFlag)	Constructs the histogram calculation object for an image.
AlgorithmHistogram(ModelImage image, int summaryBins, boolean maskFlag, boolean displayGraph, boolean userLimits, double userMin, double userMax)	Constructs the histogram calculation object for an image.
AlgorithmHistogram(ModelImage image, int summaryBins, int RGBOffset)	Constructs the histogram calculation object for an RGB image.
AlgorithmHistogram(ModelImage image, int summaryBins, int RGBOffset, boolean maskFlag)	Constructs the histogram calculation object for an RGB image.
AlgorithmHistogram(ModelImage image, int summaryBins, int RGBOffset, boolean maskFlag, boolean displayGraph, boolean userLimits, double userMin, double userMax)	Constructs the histogram calculation object for an RGB image.
AlgorithmHistogram(ModelImage image, int summaryBins, int processMode, boolean displayGraph, boolean userLimits, float userMin, float userMax)	Constructs the histogram calculation object for an image.
AlgorithmHistogram(ModelImage image, int summaryBins, int RGBOffset, int processMode, boolean displayGraph, boolean userLimits, float userMin, float userMax)	Constructs the histogram calculation object for an RGB image.

Method Summary

Modifier and Type	Method	Description
void	disposeLocal()	Dispose of local variables.
void	entireImage(boolean flag)	Sets a flag to indicate if the histogram is to be calculated for the entire image or just the VOI.
private int	entropySplit(int[] hist)	Calculate maximum entropy split of a histogram.
void	finalize()	Prepares this class for destruction.
double[]	getHighValue()	DOCUMENT ME!
int[]	getHistoBuffer()	The buffer of all histogram values.
double[]	getLowValue()	DOCUMENT ME!
ModelHistogram	getModelHistogram()	Accessor to the histogram.
private int	otsuThreshold(ModelImage image, int[] histoBuffer)	This algorithm is an implementation of Otsu thresholding technique based on the minimization of inter-class variance [otsu79].
void	runAlgorithm()	Calculates the histogram.
void	runData(int bins, int VOINum)	Calculates the histogram and outputs the number of counts per bin and area/volume information.

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, isVirtual, join, join, join, join, ofPlatform, ofVirtual, onSpinWait, resume, setContextClassLoader, setDaemon, setDefaultUncaughtExceptionHandler, setName, setPriority, setUncaughtExceptionHandler, sleep, sleep, sleep, start, startVirtualThread, stop, suspend, threadId, toString, yield

Methods inherited from class java.lang.Object

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

Field Details

WHOLE_IMAGE

private static final int WHOLE_IMAGE

See Also:

• Constant Field Values

TOTAL_VOIS

private static final int TOTAL_VOIS

See Also:

• Constant Field Values

SEPARATE_VOIS

private static final int SEPARATE_VOIS

See Also:

• Constant Field Values

dataOutput

private boolean dataOutput

Flag indicating whether or not histogram data is output to the data window.

entireImage

private boolean entireImage

If true the histogram should be calculated for the entire image.

highValue

private double[] highValue

DOCUMENT ME!

histoBuffer

private int[] histoBuffer

DOCUMENT ME!

histogram

private ModelHistogram histogram

Reference to the histogram storage object.

image

private ModelImage image

Reference to the image.

lowValue

private double[] lowValue

DOCUMENT ME!

RGBOffset

private int RGBOffset

Indicates which channel of the RGB image the histogram should be calculated. 1 = Red channel 2 = Green channel 3 = Blue channel

summaryBins

private int summaryBins

Used to indicate the number of histogram bins when using the constructors that do NOT pass in the histogram object.

displayGraph

private boolean displayGraph

userLimits

private boolean userLimits

userMin

private double userMin

userMax

private double userMax

processMode

private int processMode

Constructor Details

AlgorithmHistogram

public AlgorithmHistogram(ModelImage image,
 int summaryBins)

Constructs the histogram calculation object for an image.

Parameters:

image - ModelImage the image

summaryBins - number of bins in the histogram

AlgorithmHistogram

public AlgorithmHistogram(ModelHistogram histogram,
 ModelImage image,
 boolean maskFlag)

Constructs the histogram calculation object.

Parameters:

histogram - model of a histogram

image - model of the source image

maskFlag - Flag that indicates that the histogram will be calculated for the whole image if equal to true

AlgorithmHistogram

public AlgorithmHistogram(ModelImage image,
 int summaryBins,
 boolean maskFlag)

Constructs the histogram calculation object for an image.

Parameters:

image - ModelImage the image

summaryBins - number of bins in the histogram

maskFlag - Flag that indicates that the histogram will be calculated for the whole image if equal to true

AlgorithmHistogram

public AlgorithmHistogram(ModelImage image,
 int summaryBins,
 int processMode,
 boolean displayGraph,
 boolean userLimits,
 float userMin,
 float userMax)

Constructs the histogram calculation object for an image.

Parameters:

image - ModelImage the image

summaryBins - number of bins in the histogram

processMode - WHOLE_IMAGE, TOTAL_VOIS, or SEPARATE_VOIS

displayGraph - If true, produces a graph for display

userLimits - If true, histogram goes from userMin to userMax instead of image.getMin() to image.getMax()

userMin -

usermax -

AlgorithmHistogram

public AlgorithmHistogram(ModelImage image,
 int summaryBins,
 boolean maskFlag,
 boolean displayGraph,
 boolean userLimits,
 double userMin,
 double userMax)

Constructs the histogram calculation object for an image.

Parameters:

image - ModelImage the image

summaryBins - number of bins in the histogram

maskFlag - Flag that indicates that the histogram will be calculated for the whole image if equal to true

displayGraph - If true, produces a graph for display

userLimits - If true, histogram goes from userMin to userMax instead of image.getMin() to image.getMax()

userMin -

usermax -

AlgorithmHistogram

public AlgorithmHistogram(ModelImage image,
 int summaryBins,
 int RGBOffset)

Constructs the histogram calculation object for an RGB image.

Parameters:

image - ModelImage the image

summaryBins - number of bins in the histogram

RGBOffset - correct offset for RED = 1 , GREEN = 2, or BLUE = 3 component to be exported

AlgorithmHistogram

public AlgorithmHistogram(ModelHistogram histogram,
 int RGBOffset,
 ModelImage image,
 boolean maskFlag)

Constructs the histogram calculation object for an RGB image.

Parameters:

histogram - model of a histogram for a RGB component

RGBOffset - correct offset for RED = 1 , GREEN = 2, or BLUE = 3 component to be exported

image - model of the source image

maskFlag - Flag that indicates that the histogram will be calculated for the whole image if equal to true

AlgorithmHistogram

public AlgorithmHistogram(ModelImage image,
 int summaryBins,
 int RGBOffset,
 boolean maskFlag)

Constructs the histogram calculation object for an RGB image.

Parameters:

image - ModelImage the image

summaryBins - number of bins in the histogram

RGBOffset - correct offset for RED = 1 , GREEN = 2, or BLUE = 3 component to be exported

maskFlag - Flag that indicates that the histogram will be calculated for the whole image if equal to true

AlgorithmHistogram

public AlgorithmHistogram(ModelImage image,
 int summaryBins,
 int RGBOffset,
 int processMode,
 boolean displayGraph,
 boolean userLimits,
 float userMin,
 float userMax)

Constructs the histogram calculation object for an RGB image.

Parameters:

image - ModelImage the image

summaryBins - number of bins in the histogram

RGBOffset - correct offset for RED = 1 , GREEN = 2, or BLUE = 3 component to be exported

processMode - WHOLE_IMAGE, TOTAL_VOIS, or SEPARATE_VOIS

displayGraph - If true, produces a graph for display * @param userLimits If true, histogram goes from userMin to userMax instead of image.getMin() to image.getMax()

userMin -

usermax -

AlgorithmHistogram

public AlgorithmHistogram(ModelImage image,
 int summaryBins,
 int RGBOffset,
 boolean maskFlag,
 boolean displayGraph,
 boolean userLimits,
 double userMin,
 double userMax)

Constructs the histogram calculation object for an RGB image.

Parameters:

image - ModelImage the image

summaryBins - number of bins in the histogram

RGBOffset - correct offset for RED = 1 , GREEN = 2, or BLUE = 3 component to be exported

maskFlag - Flag that indicates that the histogram will be calculated for the whole image if equal to true

displayGraph - If true, produces a graph for display * @param userLimits If true, histogram goes from userMin to userMax instead of image.getMin() to image.getMax()

userMin -

usermax -

Method Details

disposeLocal

public void disposeLocal()

Dispose of local variables.

entireImage

public void entireImage(boolean flag)

Sets a flag to indicate if the histogram is to be calculated for the entire image or just the VOI.

Parameters:

flag - true = histogram of entire image, false = histogram of VOI

finalize

public void finalize()

Prepares this class for destruction.

Overrides:

finalize in class AlgorithmBase

getHighValue

public double[] getHighValue()

DOCUMENT ME!

Returns:

double[]

getHistoBuffer

public int[] getHistoBuffer()

The buffer of all histogram values.

Returns:

int[]

getLowValue

public double[] getLowValue()

DOCUMENT ME!

Returns:

double[]

getModelHistogram

public ModelHistogram getModelHistogram()

Accessor to the histogram.

Returns:

returns the model of the histogram

runAlgorithm

public void runAlgorithm()

Calculates the histogram.

Specified by:

runAlgorithm in class AlgorithmBase

runData

public void runData(int bins,
 int VOINum)

Calculates the histogram and outputs the number of counts per bin and area/volume information.

Parameters:

bins - number of bins in the histogram

entropySplit

private int entropySplit(int[] hist)

Calculate maximum entropy split of a histogram. This method is very similar to Otsu's method. Rather than maximising the inter-class variance, it maximizes the inter-class entropy. Entropy is a measure of the uncertainity of an event taking place. You can calculate it as: S = -(sum)p*log2(p) so it is very straightforward to do using the histogram data. (p is the probability of a pixel greyscale value in the image, and (sum) is the greek capital sigma. It is customary to use log in base 2. P.K. Sahoo, S. Soltani, K.C. Wong and, Y.C. Chen "A Survey of Thresholding Techniques", Computer Vision, Graphics, and Image Processing, Vol. 41, pp.233-260, 1988.

Parameters:

hist - histogram to be thresholded.

Returns:

index of the maximum entropy split.`

Throws:

IllegalArgumentException - DOCUMENT ME!

otsuThreshold

private int otsuThreshold(ModelImage image,
 int[] histoBuffer)

This algorithm is an implementation of Otsu thresholding technique based on the minimization of inter-class variance [otsu79].

Parameters:

image - DOCUMENT ME!

histoBuffer - DOCUMENT ME!

Returns:

DOCUMENT ME!