de.unihalle.informatik.MiToBo.fields

Class GVFFieldCalculator2D

java.lang.Object

de.unihalle.informatik.Alida.operator.ALDOperator

de.unihalle.informatik.MiToBo.core.operator.MTBOperator

de.unihalle.informatik.MiToBo.fields.GVFFieldCalculator2D

All Implemented Interfaces:

de.unihalle.informatik.Alida.datatypes.ALDConfigurationValidator, de.unihalle.informatik.Alida.operator.events.ALDOperatorExecutionProgressEventListener, EventListener

@ALDAOperator(genericExecutionMode=NONE,
              level=STANDARD)
public class GVFFieldCalculator2D
extends MTBOperator

Class to calculate a special 2D vector field, a Gradient Vector Flow Field (GVF) with its x- and y-flows from the given image. The GVF field is used as external energy in the snake calculation.

Author:

Danny Misiak

Nested Class Summary

Nested classes/interfaces inherited from class de.unihalle.informatik.Alida.operator.ALDOperator

de.unihalle.informatik.Alida.operator.ALDOperator.HidingMode, de.unihalle.informatik.Alida.operator.ALDOperator.HistoryConstructionMode

Field Summary

Fields

Modifier and Type	Field and Description
private int	height Size of the image and the calculated gvf field in y-direction.
private MTBImage	inputImage The input image as base for the GVF field calculation.
protected double[]	myX The flows of the field in x- and y-direction.
protected double[]	myY The flows of the field in x- and y-direction.
private int	numIterations Number of iterations for calculating the GVF field.
private MTBImage.MTBImageType	type Type of the input image and later the type of the calculated 2D vector field.
private MTBVectorField2D	vectorField The calculated GVF vector field.
private int	width Size of the image and the calculated gvf field in x-direction.
protected double[]	xFlow The flows of the field in x- and y-direction.
protected double[]	yFlow The flows of the field in x- and y-direction.

Fields inherited from class de.unihalle.informatik.Alida.operator.ALDOperator

completeDAG, name, operatorExecutionEventlistenerList, portHashAccess, verbose, versionProvider

Constructor Summary

Constructors

Constructor and Description
GVFFieldCalculator2D() Standard constructor.
GVFFieldCalculator2D(MTBImage inImg, int iterations) Constructor.

Method Summary

Modifier and Type	Method and Description
protected double[]	Abl_X(double[] values, int w, int h) Calculate the x-derivative of the gradient image.
protected double[]	Abl_Y(double[] values, int w, int h) Calculate the y-derivative of the gradient image.
protected double[]	BoundEnsure(double[] A, int w, int h) Test the image boundary.
protected double[]	BoundExpand(double[] A, int w, int h) Expand the image boundary.
protected double[]	BoundShrink(double[] A, int w, int h) Shrink the image boundary.
protected void	calcGVF() Calculate the GVF field with the given number of iterations on the given input image.
int	getHeight() Get image height.
MTBImage	getInputImage() Get input image.
int	getNumIterations() Get number of iterations for the GVF field.
MTBImage.MTBImageType	getType() Get input image type.
protected double[]	getValues() Get the double values of the given image.
MTBVectorField2D	getVectorField() Get calculated GVF vector field..
int	getWidth() Get image width.
protected void	normValues() Normalize the values in the gvf field in a range of [-1,1].
protected void	operate() This method does the actual work.
void	setHeight(int h) Set image height.
void	setInputImage(MTBImage inImg) Set input image.
void	setNumIterations(int iterations) Set number of iterations for the GVF field.
void	setWidth(int w) Set image width.

Methods inherited from class de.unihalle.informatik.MiToBo.core.operator.MTBOperator

readResolve

Methods inherited from class de.unihalle.informatik.Alida.operator.ALDOperator

addOperatorExecutionProgressEventListener, addParameter, addParameter, addParameterUnconditioned, fieldContained, fireOperatorExecutionProgressEvent, getALDPortHashAccessKey, getConstructionMode, getDocumentation, getHidingMode, getInactiveParameterNames, getInInoutNames, getInInoutNames, getInNames, getInOutNames, getMissingRequiredInputs, getName, getNumParameters, getOutInoutNames, getOutNames, getParameter, getParameterDescriptor, getParameterDescriptorUnconditioned, getParameterNames, getParameterUnconditioned, getSupplementalNames, getVerbose, getVersion, handleOperatorExecutionProgressEvent, hasInOutParameters, hasParameter, isAnnotatedParameter, isConfigured, print, print, print, printInterface, printInterface, readHistory, reinitializeParameterDescriptors, removeOperatorExecutionProgressEventListener, removeParameter, runOp, runOp, runOp, setConstructionMode, setConstructionMode, setConstructionMode, setHidingMode, setName, setParameter, setParameterUnconditioned, setVerbose, toStringVerbose, unconfiguredItems, validate, validateCustom, validateGeneric, writeHistory, writeHistory, writeHistory

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

width

private transient int width

Size of the image and the calculated gvf field in x-direction.

height

private transient int height

Size of the image and the calculated gvf field in y-direction.

type

private transient MTBImage.MTBImageType type

Type of the input image and later the type of the calculated 2D vector field.

numIterations

@Parameter(label="numIterations",
           required=true,
           direction=IN,
           description="Number of GVF field iterations")
private int numIterations

Number of iterations for calculating the GVF field.

inputImage

@Parameter(label="inputImage",
           required=true,
           direction=IN,
           description="Input image")
private transient MTBImage inputImage

The input image as base for the GVF field calculation.

vectorField

@Parameter(label="vectorField",
           required=true,
           direction=IN,
           description="Gradient vector field of the 2D image.")
private transient MTBVectorField2D vectorField

The calculated GVF vector field.

myX

protected transient double[] myX

The flows of the field in x- and y-direction.

myY

protected transient double[] myY

The flows of the field in x- and y-direction.

xFlow

protected transient double[] xFlow

The flows of the field in x- and y-direction.

yFlow

protected transient double[] yFlow

The flows of the field in x- and y-direction.

Constructor Detail

GVFFieldCalculator2D

public GVFFieldCalculator2D()
                     throws de.unihalle.informatik.Alida.exceptions.ALDOperatorException

Standard constructor. A new empty operator object is initialized.

Throws:

de.unihalle.informatik.Alida.exceptions.ALDOperatorException

GVFFieldCalculator2D

public GVFFieldCalculator2D(MTBImage inImg,
                            int iterations)
                     throws de.unihalle.informatik.Alida.exceptions.ALDOperatorException

Constructor. A new operator object is initialized.

Parameters:

inImg - image to work on

iterations - number of iterations for the gvf field

Throws:

de.unihalle.informatik.Alida.exceptions.ALDOperatorException

Method Detail

getInputImage

public MTBImage getInputImage()

Get input image.

setInputImage

public void setInputImage(MTBImage inImg)

Set input image.

getNumIterations

public int getNumIterations()

Get number of iterations for the GVF field.

setNumIterations

public void setNumIterations(int iterations)

Set number of iterations for the GVF field.

getType

public MTBImage.MTBImageType getType()

Get input image type.

getVectorField

public MTBVectorField2D getVectorField()

Get calculated GVF vector field..

getWidth

public int getWidth()

Get image width.

setWidth

public void setWidth(int w)

Set image width.

getHeight

public int getHeight()

Get image height.

setHeight

public void setHeight(int h)

Set image height.

operate

protected void operate()
                throws de.unihalle.informatik.Alida.exceptions.ALDOperatorException

This method does the actual work. Each subclass needs to overwrite this method. As parameter a MiToBo parameter object is passed to the function where all required data and operator configuration information can be found.

Specified by:

operate in class de.unihalle.informatik.Alida.operator.ALDOperator

Throws:

de.unihalle.informatik.Alida.exceptions.ALDOperatorException

calcGVF

protected void calcGVF()

Calculate the GVF field with the given number of iterations on the given input image.

getValues

protected double[] getValues()

Get the double values of the given image.

Returns:

Double values of the given image in a one dimensional double array.

normValues

protected void normValues()

Normalize the values in the gvf field in a range of [-1,1].

Abl_X

protected double[] Abl_X(double[] values,
                         int w,
                         int h)

Calculate the x-derivative of the gradient image.

Parameters:

values - gradient values of the image

w - width of the given image

h - height of the given image

Returns:

A one dimensional array including the x-derivative values

Abl_Y

protected double[] Abl_Y(double[] values,
                         int w,
                         int h)

Calculate the y-derivative of the gradient image.

Parameters:

values - gradient values of the image

w - width of the given image

h - height of the given image

Returns:

A one dimensional array including the y-derivative values

BoundExpand

protected double[] BoundExpand(double[] A,
                               int w,
                               int h)

Expand the image boundary. It's necessary to calculate the derivatives in the border pixels of the image.

Parameters:

A - gradient image of the given image

w - width of the given image

h - height of the given image

BoundEnsure

protected double[] BoundEnsure(double[] A,
                               int w,
                               int h)

Test the image boundary. It's necessary to calculate the derivatives in the border pixels of the image.

Parameters:

A - gradient image of the given image

w - width of the given image

h - height of the given image

BoundShrink

protected double[] BoundShrink(double[] A,
                               int w,
                               int h)

Shrink the image boundary. It's necessary to calculate the derivatives in the border pixels of the image.

Parameters:

A - gradient image of the given image

w - width of the given image

h - height of the given image