itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage > Class Template Reference

#include <itkFEMRegistrationFilter.h>

Inheritance diagram for itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >:

[legend]Collaboration diagram for itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >:

[legend]List of all members.

---

Detailed Description

template<class TMovingImage, class TFixedImage>
class itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >

FEM Image registration filter.

The image registration problem is modeled here with the finite element method. Image registration is, in general, an ill-posed problem. Thus, we use an optimization scheme where the optimization criterion is given by a regularized variational energy. The variational energy arises from modeling the image as a physical body on which external forces act. The body is allowed to deform so as to minimize the applied force. The resistance of the physical body to deformation, determined by the physics associated with the body, serves to regularize the solution. The forces applied to the body are, generally, highly non-linear and so the body is allowed to deform slowly and incrementally. The direction it deforms follows the gradient of the potential energy (the force) we define. The potential energies we may choose from are given by the itk image-to-image metrics. The choices and the associated direction of descent are : Mean Squares (minimize), Normalized Cross-Correlation (maximize) Mutual Information (maximize). Note that we have to set the direction (SetDescentDirection) when we choose a metric. The forces driving the problem may also be given by user-supplied landmarks. The corners of the image, in this example, are always pinned. This example is designed for 2D or 3D images. A rectilinear mesh is generated automatically given the correct element type (Quadrilateral or Hexahedral).

Our specific Solver for this example uses trapezoidal time stepping. This is a method for solving a second-order PDE in time. The solution is penalized by the zeroth (mass matrix) and first derivatives (stiffness matrix) of the shape functions. There is an option to perform a line search on the energy after each iteration. Optimal parameter settings require experimentation. The following approach tends to work well : Choose the relative size of density to elasticity (e.g. Rho / E ~= 1.) such that the image deforms locally and slowly. This also affects the stability of the solution. Choose the time step to control the size of the deformation at each step. Choose enough iterations to allow the solution to converge (this may be automated).

Reading images is up to the user. Either set the images using SetMoving/FixedImage or see the ReadImages function.

Note:

This code works for only 2 or 3 dimensions b/c we do not have > 3D elements.

TODO : Keep the full field around (if using re-gridding). Introduce compensation for kinematic non-linearity in time (if using Eulerian frame).

Definition at line 102 of file itkFEMRegistrationFilter.h.

Public Types
typedef SmartPointer< const Self >	ConstPointer
typedef double	CoordRepType
typedef DataObject::Pointer	DataObjectPointer
typedef std::vector< DataObjectPointer >	DataObjectPointerArray
typedef VectorLinearInterpolateImageFunction< FieldType, CoordRepType >	DefaultInterpolatorType
typedef itk::VectorExpandImageFilter< FieldType, FieldType >	ExpanderType
typedef ExpanderType::ExpandFactorsType	ExpandFactorsType
typedef itk::ImageRegionIteratorWithIndex< FieldType >	FieldIterator
typedef itk::Image< VectorType, itkGetStaticConstMacro(ImageDimension)	FieldType )
typedef TFixedImage	FixedImageType
typedef itk::RecursiveMultiResolutionPyramidImageFilter< FixedImageType, FixedImageType >	FixedPyramidType
typedef double	Float
typedef itk::ImageRegionIteratorWithIndex< FloatImageType >	FloatImageIterator
typedef Image< float, itkGetStaticConstMacro(ImageDimension)	FloatImageType )
typedef itk::ImageRegionIteratorWithIndex< FixedImageType >	ImageIterator
typedef FiniteDifferenceFunctionLoad< MovingImageType, FixedImageType >	ImageMetricLoadType
typedef FixedImageType::SizeType	ImageSizeType
typedef itk::VectorIndexSelectionCastImageFilter< FieldType, FloatImageType >	IndexSelectCasterType
typedef InputImageType::ConstPointer	InputImageConstPointer
typedef InputImageType::PixelType	InputImagePixelType
typedef InputImageType::Pointer	InputImagePointer
typedef InputImageType::RegionType	InputImageRegionType
typedef TMovingImage	InputImageType
typedef InterpolatorType::Pointer	InterpolatorPointer
typedef VectorInterpolateImageFunction< FieldType, CoordRepType >	InterpolatorType
typedef std::vector< typename LoadLandmark::Pointer >	LandmarkArrayType
typedef LinearSystemWrapperItpack	LinearSystemSolverType
typedef Load::ArrayType	LoadArray
typedef MaterialLinearElasticity	MaterialType
typedef PDEDeformableRegistrationFunction< FixedImageType, MovingImageType, FieldType >	MetricBaseType
typedef MetricBaseType::Pointer	MetricBaseTypePointer
typedef TMovingImage	MovingImageType
typedef OutputImageType::PixelType	OutputImagePixelType
typedef OutputImageType::Pointer	OutputImagePointer
typedef Superclass::OutputImageRegionType	OutputImageRegionType
typedef TFixedImage	OutputImageType
typedef FixedImageType::PixelType	PixelType
typedef SmartPointer< Self >	Pointer
typedef FEMRegistrationFilter	Self
enum	Sign {   positive = 1,   negative = -1 }
typedef SolverCrankNicolson	SolverType
typedef ImageToImageFilter< TMovingImage, TFixedImage >	Superclass
typedef itk::Vector< float, itkGetStaticConstMacro(ImageDimension)	VectorType )
typedef itk::WarpImageFilter< MovingImageType, FixedImageType, FieldType >	WarperType
Public Member Functions
virtual void	AbortGenerateDataOff ()
virtual void	AbortGenerateDataOn ()
void	ChooseMetric (float whichmetric)
void	ComputeJacobian (float sign=1.0, FieldType *field=NULL, float smooth=0.0)
virtual LightObject::Pointer	CreateAnother () const
virtual void	DebugOff () const
virtual void	DebugOn () const
virtual void	Delete ()
The metric region allows one to compute the	derivative (force) of the similarity metric *using a region of size[i
void	DoLineSearch (unsigned int b)
void	DoMultiRes (bool b)
void	EmployRegridding (unsigned int b)
void	EnforceDiffeomorphism (float thresh, SolverType &S, bool onlywriteimages)
virtual void	EnlargeOutputRequestedRegion (DataObject *)
de constructor *	FEMRegistrationFilter ()
virtual const bool &	GetAbortGenerateData ()
Command *	GetCommand (unsigned long tag)
std::string	GetConfigFileName ()
bool	GetDebug () const
FieldType *	GetDeformationField ()
Float	GetElasticity (unsigned int which=0)
std::string	GetFixedFile ()
FixedImageType *	GetFixedImage ()
ImageSizeType	GetImageSize ()
const InputImageType *	GetInput (unsigned int idx)
const InputImageType *	GetInput (void)
DataObjectPointerArray &	GetInputs ()
virtual InterpolatorType *	GetInterpolator ()
FloatImageType *	GetJacobianImage ()
const MetaDataDictionary &	GetMetaDataDictionary (void) const
MetaDataDictionary &	GetMetaDataDictionary (void)
Set Get the Metric *MetricBaseTypePointer	GetMetric ()
std::string	GetMovingFile ()
MovingImageType *	GetMovingImage ()
virtual unsigned long	GetMTime () const
MultiThreader *	GetMultiThreader ()
virtual const char *	GetNameOfClass () const
std::vector< DataObjectPointer >::size_type	GetNumberOfInputs () const
std::vector< DataObjectPointer >::size_type	GetNumberOfOutputs () const
virtual const int &	GetNumberOfThreads ()
virtual std::vector< DataObjectPointer >::size_type	GetNumberOfValidRequiredInputs () const
MovingImageType *	GetOriginalMovingImage ()
OutputImageType *	GetOutput (unsigned int idx)
Get the output data of this process object The output of this *function is not valid until an appropriate either explicitly or implicitly Both the filter *itself and the data object have and both *methods update the data Here are three ways to use *	GetOutput () and make sure the data is valid.In these *examples
Return an array with all the outputs of this process object *This is useful for tracing forward in the pipeline to contruct *graphs etc *DataObjectPointerArray &	GetOutputs ()
virtual const float &	GetProgress ()
virtual int	GetReferenceCount () const
virtual const bool &	GetReleaseDataBeforeUpdateFlag ()
virtual bool	GetReleaseDataFlag () const
std::string	GetResultsFileName ()
FixedImageType *	GetWarpedImage ()
unsigned int	GetWidthOfMetricRegion (unsigned int which=0)
bool	GetWriteDisplacements ()
virtual void	GraftNthOutput (unsigned int idx, DataObject *output)
virtual void	GraftOutput (DataObject *output)
bool	HasObserver (const EventObject &event) const
Get the output data of this process object The output of this *function is not valid until an appropriate either explicitly or implicitly Both the filter *itself and the data object have and both *methods update the data Here are three ways to use *a image is a pointer to some Image and the *particular ProcessObjects involved are filters The same *examples apply to non	image (e.g.Mesh) data as well.**\code *anotherFilter->SetInput(someFilter->GetOutput())
void	InvokeEvent (const EventObject &) const
void	InvokeEvent (const EventObject &)
void	IterativeSolve (SolverType &S)
	itkStaticConstMacro (OutputImageDimension, unsigned int, TFixedImage::ImageDimension)
ImageDimension constants *	itkStaticConstMacro (InputImageDimension, unsigned int, TMovingImage::ImageDimension)
	itkStaticConstMacro (ImageDimension, unsigned int, FixedImageType::ImageDimension)
virtual DataObjectPointer	MakeOutput (unsigned int idx)
virtual void	Modified () const
void	MultiResSolve ()
virtual void	PopBackInput ()
virtual void	PopFrontInput ()
virtual void	PrepareOutputs ()
void	Print (std::ostream &os, Indent indent=0) const
void	PrintVectorField (unsigned int modnum=1000)
virtual void	PropagateRequestedRegion (DataObject *output)
Push Pop the input of this process object These methods allow a *filter to model its input vector as a queue or stack These *routines may not be appropriate for all especially *filters with different types of inputs These routines follow *the semantics of STL **The routines are useful for applications that need to process *rolling sets of images For if an application has *images and they need to run a filter on then *run the filter on then run the filter on the application can accomplish this by popping *an input off the front of the input list and push a new image *onto the back of input list this only makes sense for *filters that single type of input **Other uses are also possible For a single input pushing *and popping inputs allow the application to temporarily replace *an input to a filter **virtual void	PushBackInput (const InputImageType *image)
virtual void	PushFrontInput (const InputImageType *image)
bool	ReadConfigFile (const char *)
virtual void	Register () const
virtual void	ReleaseDataBeforeUpdateFlagOff ()
virtual void	ReleaseDataBeforeUpdateFlagOn ()
void	ReleaseDataFlagOff ()
void	ReleaseDataFlagOn ()
void	RemoveAllObservers ()
void	RemoveObserver (unsigned long tag)
virtual void	ResetPipeline ()
void	RunRegistration (void)
virtual void	SetAbortGenerateData (bool _arg)
void	SetAlpha (Float a)
void	SetConfigFileName (const char *f)
void	SetDebug (bool debugFlag) const
Sets the FE deformation field *void	SetDeformationField (FieldType *F)
void	SetDescentDirectionMaximize ()
void	SetDescentDirectionMinimize ()
void	SetDisplacementsFile (const char *r)
void	SetElasticity (Float i, unsigned int which=0)
void	SetElement (Element::Pointer e)
void	SetEnergyReductionFactor (Float i)
void	SetFixedFile (const char *t)
void	SetFixedImage (FixedImageType *T)
void	SetGamma (Float r, unsigned int which=0)
virtual void	SetInput (unsigned int, const TMovingImage *image)
Set Get the image input of this process object *virtual void	SetInput (const InputImageType *image)
virtual void	SetInterpolator (InterpolatorType *_arg)
void	SetLandmarkFile (const char *l)
void	SetLineSearchMaximumIterations (unsigned int f)
void	SetMaterial (MaterialType::Pointer m)
void	SetMaximumIterations (unsigned int i, unsigned int which)
void	SetMaxLevel (unsigned int i)
*void	SetMeshPixelsPerElementAtEachResolution (unsigned int i, unsigned int which=0)
The FEM filter can generate its own mesh for or if none is provided The mesh is generated for quadrilaterals in D and hexahedra in D This function sets the number of elements generated along each dimension at the resolution designated by which E g to generate pixels per element in each dimension in the st use	SetMeshResolution (10, 0)
void	SetMetaDataDictionary (const MetaDataDictionary &rhs)
void	SetMetric (MetricBaseTypePointer MP)
void	SetMovingFile (const char *r)
void	SetMovingImage (MovingImageType *R)
void	SetNumberOfIntegrationPoints (unsigned int i, unsigned int which=0)
Get Set the number of threads to create when executing *virtual void	SetNumberOfThreads (int _arg)
void	SetNumLevels (unsigned int i)
virtual void	SetProgress (float _arg)
virtual void	SetReferenceCount (int)
Turn on off the flags to control whether the bulk data belonging *to the outputs of this ProcessObject are released after being *used by a downstream ProcessObject Default value is off Another *options for controlling memory utilization is the *ReleaseDataBeforeUpdateFlag *virtual void	SetReleaseDataFlag (bool flag)
void	SetResultsFile (const char *r)
void	SetResultsFileName (const char *f)
void	SetRho (Float r, unsigned int which=0)
void	SetTemp (Float i)
void	SetTimeStep (Float i)
The metric region allows one to compute the i in D[i, i, i] in D *param i number of elements *param which determines the region at a given resolution of the solution process *void	SetWidthOfMetricRegion (unsigned int i, unsigned int which=0)
void	SetWriteDisplacements (bool b)
virtual void	UnRegister () const
*endcode *In the above the two lines of code can be in *either order **Note that it may be more efficient to *use a pipeline than to call	Update () once for each filter in *turn.**For an image
*endcode *In the above the two lines of code can be in *either order **Note that	Update () is not called automatically except within a *pipeline as in the first example.When\b streaming(using a *StreamingImageFilter) is activated
*endcode **code *someFilter	Update ()
*image	Update ()
*anotherFilter	Update ()
Get the output data of this process object The output of this *function is not valid until an appropriate either explicitly or implicitly Both the filter *itself and the data object have	Update () methods
Get the output data of this process object The output of this *function is not valid until an appropriate	Update () method has *been called
virtual void	UpdateLargestPossibleRegion ()
virtual void	UpdateOutputData (DataObject *output)
virtual void	UpdateOutputInformation ()
void	UpdateProgress (float amount)
void	UseLandmarks (bool b)
void	WarpImage (const MovingImageType *R)
int	WriteDisplacementField (unsigned int index)
int	WriteDisplacementFieldMultiComponent ()
void	WriteWarpedImage (const char *fn)
	~FEMRegistrationFilter ()
Static Public Member Functions
static void	BreakOnError ()
static bool	GetGlobalWarningDisplay ()
static void	GlobalWarningDisplayOff ()
static void	GlobalWarningDisplayOn ()
static Pointer	New ()
This is a global flag that controls whether any warning *or error messages are displayed *static void	SetGlobalWarningDisplay (bool flag)
Public Attributes
Allow people to add remove invoke observers(callbacks) to any ITK *object.This is an implementation of the subject/observer design *pattern.An observer is added by specifying an event to respond to *and an itk unsigned lon	AddObserver )(const EventObject &event, Command *) const
Push Pop the input of this process object These methods allow a *filter to model its input vector as a queue or stack These *routines may not be appropriate for all especially *filters with different types of inputs These routines follow *the semantics of STL **The routines are useful for applications that need to process *rolling sets of images For if an application has *images and they need to run a filter on then *run the filter on then run the filter on the application can accomplish this by popping *an input off the front of the input list and push a new image *onto the back of input list	Again
This is a global flag that controls whether any	debug
The FEM filter can generate its own mesh for or	dimensions
*endcode *In the above	example
Push Pop the input of this process object These methods allow a *filter to model its input vector as a queue or stack These *routines may not be appropriate for all especially *filters with different types of inputs These routines follow *the semantics of STL **The routines are useful for applications that need to process *rolling sets of images For if an application has *images and they need to run a filter on then *run the filter on then run the filter on the application can accomplish this by popping *an input off the front of the input list and push a new image *onto the back of input list this only makes sense for *filters that single type of input **Other uses are also possible For a single input	filter
Push Pop the input of this process object These methods allow a *filter to model its input vector as a queue or stack These *routines may not be appropriate for all	filters
*	image
*endcode **In this a someFilter and a anotherFilter are said *to constitute a b pipeline **code *	image
Push Pop the input of this process object These methods allow a *filter to model its input vector as a queue or stack These *routines may not be appropriate for all especially *filters with different types of inputs These routines follow *the semantics of STL **The routines are useful for applications that need to process *rolling sets of images For if an application has *images and they need to run a filter on then *run the filter on then run the filter on *	images
Push Pop the input of this process object These methods allow a *filter to model its input vector as a queue or stack These *routines may not be appropriate for all especially *filters with different types of inputs These routines follow *the semantics of STL **The routines are useful for applications that need to process *rolling sets of images For if an application has *images and they need to run a filter on then *run the filter on	images
Push Pop the input of this process object These methods allow a *filter to model its input vector as a queue or stack These *routines may not be appropriate for all especially *filters with different types of inputs These routines follow *the semantics of STL **The routines are useful for applications that need to process *rolling sets of images For if an application has *images and they need to run a filter on	images
Push Pop the input of this process object These methods allow a *filter to model its input vector as a queue or stack These *routines may not be appropriate for all especially *filters with different types of inputs These routines follow *the semantics of STL **The routines are useful for applications that need to process *rolling sets of images For	instance
Get the output data of this process object The output of this *function is not valid until an appropriate either explicitly or implicitly Both the filter *itself and the data object have and both *methods update the data Here are three ways to use *a image is a pointer to some Image	object
*endcode *In the above the two lines of code can be in *either order **Note that it may be more efficient to *use a pipeline than to call the data generated is for the requested *	Region
The FEM filter can generate its own mesh for or if none is provided The mesh is generated for quadrilaterals in D and hexahedra in D This function sets the number of elements generated along each dimension at the resolution designated by which E g to generate pixels per element in each dimension in the st	resolution
*endcode **In this	situation
Protected Types
typedef ImageToImageFilterDetail::ImageRegionCopier< itkGetStaticConstMacro(OutputImageDimension), itkGetStaticConstMacro(InputImageDimension)	InputToOutputRegionCopierType )
typedef ImageToImageFilterDetail::ImageRegionCopier< itkGetStaticConstMacro(InputImageDimension), itkGetStaticConstMacro(OutputImageDimension)	OutputToInputRegionCopierType )
Protected Member Functions
virtual void	AddInput (DataObject *input)
virtual void	AddOutput (DataObject *output)
virtual void	AfterThreadedGenerateData ()
virtual void	AllocateOutputs ()
void	ApplyImageLoads (SolverType &S, MovingImageType *i1, FixedImageType *i2)
void	ApplyLoads (SolverType &S, ImageSizeType Isz, double *spacing=NULL)
virtual void	BeforeThreadedGenerateData ()
virtual void	CacheInputReleaseDataFlags ()
virtual void	CallCopyInputRegionToOutputRegion (OutputImageRegionType &destRegion, const InputImageRegionType &srcRegion)
virtual void	CallCopyOutputRegionToInputRegion (InputImageRegionType &destRegion, const OutputImageRegionType &srcRegion)
void	CreateLinearSystemSolver ()
void	CreateMesh (double ElementsPerSide, Solver &S, ImageSizeType sz)
Float	EvaluateEnergy ()
Float	EvaluateResidual (SolverType &mySolver, Float t)
void	FindBracketingTriplet (SolverType &mySolver, Float *a, Float *b, Float *c)
virtual void	GenerateData ()
virtual void	GenerateInputRequestedRegion ()
virtual void	GenerateOutputInformation ()
virtual void	GenerateOutputRequestedRegion (DataObject *output)
const DataObject *	GetInput (unsigned int idx) const
Set the solver s current load *virtual ImageMetricLoadType *	GetLoad ()
FloatImageType *	GetMetricImage (FieldType *F)
virtual const unsigned int &	GetNumberOfRequiredInputs ()
virtual const unsigned int &	GetNumberOfRequiredOutputs ()
const DataObject *	GetOutput (unsigned int idx) const
Float	GoldenSection (SolverType &mySolver, Float tol=0.01, unsigned int MaxIters=25)
	ImageSource ()
	ImageToImageFilter ()
void	InterpolateVectorField (SolverType &S)
bool	PrintObservers (std::ostream &os, Indent indent) const
void	PrintSelf (std::ostream &os, Indent indent) const
virtual void	PrintTrailer (std::ostream &os, Indent indent) const
virtual void	PropagateResetPipeline ()
**these methods end of hiding the versions from the superclass *ProcessObject whose arguments are DataObjects we re expose *the versions from ProcessObject to avoid warnings about hiding *methods from the superclass *void	PushBackInput (const DataObject *input)
*	PushBackInput ()
*	PushFronInput () in the public section force the *input to be the type expected by an ImageToImageFilter.However
void	PushFrontInput (const DataObject *input)
virtual void	ReleaseInputs ()
virtual void	RemoveInput (DataObject *input)
virtual void	RemoveOutput (DataObject *output)
virtual void	RestoreInputReleaseDataFlags ()
void	SampleVectorFieldAtNodes (SolverType &S)
Protected methods for setting inputs *Subclasses make use of them for setting input *virtual void	SetNthInput (unsigned int num, DataObject *input)
Protected methods for setting outputs *Subclasses make use of them for getting output *virtual void	SetNthOutput (unsigned int num, DataObject *output)
void	SetNumberOfInputs (unsigned int num)
void	SetNumberOfOutputs (unsigned int num)
virtual void	SetNumberOfRequiredInputs (unsigned int _arg)
virtual void	SetNumberOfRequiredOutputs (unsigned int _arg)
virtual int	SplitRequestedRegion (int i, int num, OutputImageRegionType &splitRegion)
virtual void	ThreadedGenerateData (const OutputImageRegionType &outputRegionForThread, int threadId)
Static Protected Member Functions
static ITK_THREAD_RETURN_TYPE	ThreaderCallback (void *arg)
Protected Attributes
Re size the vector field(smaller to larger).*/typedef typename FieldType FieldPointe	ExpandVectorField )(ExpandFactorsType *expandFactors, FieldType *f)
**these methods end of hiding the versions from the superclass *ProcessObject whose arguments are DataObjects	Here
TimeStamp	m_OutputInformationMTime
int	m_ReferenceCount
SimpleFastMutexLock	m_ReferenceCountLock
bool	m_Updating
Methods invoked by virtual Print() to print information about the object *including superclasses.Typically not called by the user(use Print()*instead) but used in the hierarchical print process to combine the *output of several classes.*/virtual void PrintSelf(std voi	PrintHeader )(std::ostream &os, Indent indent) const
Classes
class	FEMOF

---

Member Typedef Documentation

template<class TMovingImage, class TFixedImage> typedef SmartPointer<const Self> itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::ConstPointer

Reimplemented from itk::ImageToImageFilter< TMovingImage, TFixedImage >. Definition at line 108 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef double itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::CoordRepType

Typedef support for the interpolation function Definition at line 145 of file itkFEMRegistrationFilter.h.

typedef DataObject::Pointer itk::ImageSource< TFixedImage >::DataObjectPointer [inherited]

Smart Pointer type to a DataObject. Reimplemented from itk::ProcessObject. Definition at line 62 of file itkImageSource.h.

typedef std::vector<DataObjectPointer> itk::ProcessObject::DataObjectPointerArray [inherited]

STL Array of SmartPointers to DataObjects Definition at line 103 of file itkProcessObject.h.

template<class TMovingImage, class TFixedImage> typedef VectorLinearInterpolateImageFunction<FieldType,CoordRepType> itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::DefaultInterpolatorType

Definition at line 150 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef itk::VectorExpandImageFilter<FieldType,FieldType> itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::ExpanderType

Definition at line 156 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef ExpanderType::ExpandFactorsType itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::ExpandFactorsType

Definition at line 160 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef itk::ImageRegionIteratorWithIndex<FieldType> itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::FieldIterator

Definition at line 140 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef itk::Image<VectorType,itkGetStaticConstMacro(ImageDimension) itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::FieldType)

Definition at line 135 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef TFixedImage itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::FixedImageType

Definition at line 117 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef itk::RecursiveMultiResolutionPyramidImageFilter<FixedImageType,FixedImageType> itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::FixedPyramidType

Definition at line 163 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef double itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::Float

Definition at line 129 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef itk::ImageRegionIteratorWithIndex<FloatImageType> itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::FloatImageIterator

Definition at line 139 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef Image< float, itkGetStaticConstMacro(ImageDimension) itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::FloatImageType)

Definition at line 125 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef itk::ImageRegionIteratorWithIndex<FixedImageType> itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::ImageIterator

Definition at line 138 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef FiniteDifferenceFunctionLoad<MovingImageType,FixedImageType> itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::ImageMetricLoadType

Instantiate the load class with the correct image type. Definition at line 171 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef FixedImageType::SizeType itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::ImageSizeType

Definition at line 119 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef itk::VectorIndexSelectionCastImageFilter<FieldType,FloatImageType> itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::IndexSelectCasterType

Definition at line 141 of file itkFEMRegistrationFilter.h.

typedef InputImageType::ConstPointer itk::ImageToImageFilter< TMovingImage , TFixedImage >::InputImageConstPointer [inherited]

Definition at line 83 of file itkImageToImageFilter.h.

typedef InputImageType::PixelType itk::ImageToImageFilter< TMovingImage , TFixedImage >::InputImagePixelType [inherited]

Definition at line 85 of file itkImageToImageFilter.h.

typedef InputImageType::Pointer itk::ImageToImageFilter< TMovingImage , TFixedImage >::InputImagePointer [inherited]

Definition at line 82 of file itkImageToImageFilter.h.

typedef InputImageType::RegionType itk::ImageToImageFilter< TMovingImage , TFixedImage >::InputImageRegionType [inherited]

Definition at line 84 of file itkImageToImageFilter.h.

typedef TMovingImage itk::ImageToImageFilter< TMovingImage , TFixedImage >::InputImageType [inherited]

Some convenient typedefs. Definition at line 81 of file itkImageToImageFilter.h.

typedef ImageToImageFilterDetail::ImageRegionCopier<itkGetStaticConstMacro(OutputImageDimension), itkGetStaticConstMacro(InputImageDimension) itk::ImageToImageFilter< TMovingImage , TFixedImage >::InputToOutputRegionCopierType) [protected, inherited]

Typedef for the region copier function object that converts an input region to an output region. Definition at line 163 of file itkImageToImageFilter.h.

template<class TMovingImage, class TFixedImage> typedef InterpolatorType::Pointer itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::InterpolatorPointer

Definition at line 148 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef VectorInterpolateImageFunction<FieldType,CoordRepType> itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::InterpolatorType

Definition at line 147 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef std::vector<typename LoadLandmark::Pointer> itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::LandmarkArrayType

Definition at line 133 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef LinearSystemWrapperItpack itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::LinearSystemSolverType

Definition at line 126 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef Load::ArrayType itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::LoadArray

Definition at line 130 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef MaterialLinearElasticity itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::MaterialType

Definition at line 137 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef PDEDeformableRegistrationFunction<FixedImageType,MovingImageType,FieldType> itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::MetricBaseType

Definition at line 172 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef MetricBaseType::Pointer itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::MetricBaseTypePointer

Definition at line 174 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef TMovingImage itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::MovingImageType

Definition at line 114 of file itkFEMRegistrationFilter.h.

typedef OutputImageType::PixelType itk::ImageSource< TFixedImage >::OutputImagePixelType [inherited]

Definition at line 71 of file itkImageSource.h.

typedef OutputImageType::Pointer itk::ImageSource< TFixedImage >::OutputImagePointer [inherited]

Definition at line 69 of file itkImageSource.h.

typedef Superclass::OutputImageRegionType itk::ImageToImageFilter< TMovingImage , TFixedImage >::OutputImageRegionType [inherited]

Superclass typedefs. Reimplemented from itk::ImageSource< TFixedImage >. Definition at line 75 of file itkImageToImageFilter.h.

typedef TFixedImage itk::ImageSource< TFixedImage >::OutputImageType [inherited]

Some convenient typedefs. Definition at line 65 of file itkImageSource.h.

typedef ImageToImageFilterDetail::ImageRegionCopier<itkGetStaticConstMacro(InputImageDimension), itkGetStaticConstMacro(OutputImageDimension) itk::ImageToImageFilter< TMovingImage , TFixedImage >::OutputToInputRegionCopierType) [protected, inherited]

Typedef for the region copier function object that converts an output region to an input region. Definition at line 168 of file itkImageToImageFilter.h.

template<class TMovingImage, class TFixedImage> typedef FixedImageType::PixelType itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::PixelType

Definition at line 118 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef SmartPointer<Self> itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::Pointer

Reimplemented from itk::ImageToImageFilter< TMovingImage, TFixedImage >. Definition at line 107 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef FEMRegistrationFilter itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::Self

Standard class typedefs. Reimplemented from itk::ImageToImageFilter< TMovingImage, TFixedImage >. Definition at line 105 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef SolverCrankNicolson itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SolverType

Definition at line 127 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef ImageToImageFilter<TMovingImage, TFixedImage> itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::Superclass

Reimplemented from itk::ImageToImageFilter< TMovingImage, TFixedImage >. Definition at line 106 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef itk::Vector<float,itkGetStaticConstMacro(ImageDimension) itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::VectorType)

Definition at line 134 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> typedef itk::WarpImageFilter<MovingImageType,FixedImageType, FieldType> itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::WarperType

Definition at line 136 of file itkFEMRegistrationFilter.h.

---

Member Enumeration Documentation

template<class TMovingImage, class TFixedImage> enum itk::fem::FEMRegistrationFilter::Sign

Enumeration values: positive  negative  Definition at line 128 of file itkFEMRegistrationFilter.h.

---

Constructor & Destructor Documentation

template<class TMovingImage, class TFixedImage> de constructor* itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::FEMRegistrationFilter (   )

template<class TMovingImage, class TFixedImage> itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::~FEMRegistrationFilter (   )

---

Member Function Documentation

virtual void itk::ProcessObject::AbortGenerateDataOff (   )  [virtual, inherited]

virtual void itk::ProcessObject::AbortGenerateDataOn (   )  [virtual, inherited]

Turn on and off the AbortGenerateData flag.

virtual void itk::ProcessObject::AddInput (  DataObject *  input  )  [protected, virtual, inherited]

virtual void itk::ProcessObject::AddOutput (  DataObject *  output  )  [protected, virtual, inherited]

virtual void itk::ImageSource< TFixedImage >::AfterThreadedGenerateData (   )  [inline, protected, virtual, inherited]

If an imaging filter needs to perform processing after all processing threads have completed, the filter can can provide an implementation for AfterThreadedGenerateData(). The execution flow in the default GenerateData() method will be: 1) Allocate the output buffer 2) Call BeforeThreadedGenerateData() 3) Spawn threads, calling ThreadedGenerateData() in each thread. 4) Call AfterThreadedGenerateData() Note that this flow of control is only available if a filter provides a ThreadedGenerateData() method and NOT a GenerateData() method. Definition at line 254 of file itkImageSource.h.

virtual void itk::ImageSource< TFixedImage >::AllocateOutputs (   )  [protected, virtual, inherited]

The GenerateData method normally allocates the buffers for all of the outputs of a filter. Some filters may want to override this default behavior. For example, a filter may have multiple outputs with varying resolution. Or a filter may want to process data in place by grafting its input to its output.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::ApplyImageLoads (  SolverType &  S, MovingImageType *  i1, FixedImageType *  i2 )  [protected]

The image loads are entered into the solver.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::ApplyLoads (  SolverType &  S, ImageSizeType  Isz, double *  spacing = NULL )  [protected]

The non-image loads are entered into the solver.

virtual void itk::ImageSource< TFixedImage >::BeforeThreadedGenerateData (  void   )  [inline, protected, virtual, inherited]

If an imaging filter needs to perform processing after the buffer has been allocated but before threads are spawned, the filter can can provide an implementation for BeforeThreadedGenerateData(). The execution flow in the default GenerateData() method will be: 1) Allocate the output buffer 2) Call BeforeThreadedGenerateData() 3) Spawn threads, calling ThreadedGenerateData() in each thread. 4) Call AfterThreadedGenerateData() Note that this flow of control is only available if a filter provides a ThreadedGenerateData() method and NOT a GenerateData() method. Definition at line 242 of file itkImageSource.h.

static void itk::LightObject::BreakOnError (   )  [static, inherited]

This method is called when itkExceptionMacro executes. It allows the debugger to break on error.

virtual void itk::ProcessObject::CacheInputReleaseDataFlags (   )  [protected, virtual, inherited]

Cache the state of any ReleaseDataFlag's on the inputs. While the filter is executing, we need to set the ReleaseDataFlag's on the inputs to false in case the current filter is implemented using a mini-pipeline (which will try to release the inputs). After the filter finishes, we restore the state of the ReleaseDataFlag's before the call to ReleaseInputs().

virtual void itk::ImageToImageFilter< TMovingImage , TFixedImage >::CallCopyInputRegionToOutputRegion (  OutputImageRegionType &  destRegion, const InputImageRegionType &  srcRegion )  [protected, virtual, inherited]

This function calls the actual region copier to do the mapping from input image space to output image space. It uses a Function object used for dispatching to various routines to copy an input region (start index and size) to an output region. For most filters, this is a trivial copy because most filters require the input dimension to match the output dimension. However, some filters like itk::UnaryFunctorImageFilter can support output images of a higher dimension that the input. This function object is used by the default implementation of GenerateOutputInformation(). It can also be used in routines like ThreadedGenerateData() where a filter may need to map an input region to an output region. The default copier uses a "dispatch pattern" to call one of three overloaded functions depending on whether the input and output images are the same dimension, the input is a higher dimension that the output, or the input is of a lower dimension than the output. The use of an overloaded function is required for proper compilation of the various cases. For the latter two cases, trivial implementations are used. If the input image is a higher dimension than the output, the first portion of the input region is copied to the output region. If the input region is a lower dimension than the output, the input region information is copied into the first portion of the output region and the rest of the output region is set to zero. If a filter needs a different default behavior, it can override this method.

virtual void itk::ImageToImageFilter< TMovingImage , TFixedImage >::CallCopyOutputRegionToInputRegion (  InputImageRegionType &  destRegion, const OutputImageRegionType &  srcRegion )  [protected, virtual, inherited]

This function calls the actual region copier to do the mapping from output image space to input image space. It uses a Function object used for dispatching to various routines to copy an output region (start index and size) to an input region. For most filters, this is a trivial copy because most filters require the input dimension to match the output dimension. However, some filters like itk::ExtractImageFilter can support output images of a lower dimension that the input. This function object can be used by GenerateOutputInformation() to copy the input LargestPossibleRegion to the output LargestPossibleRegion and can also be used in GenerateData or ThreadedGenerateData() where a filter may need to map an output region to an input region. The default copier uses a "dispatch pattern" to call one of three overloaded functions depending on whether the input and output images are the same dimension, the input is a higher dimension that the output, or the input is of a lower dimension than the output. The use of an overloaded function is required for proper compilation of the various cases. For the latter two cases, trivial implementations are used. If the input image is a higher dimension than the output, the output region information is copied into the first portion of the input region and the rest of the input region is set to zero. If the input region is a lower dimension than the output, the first portion of the output region is copied to the input region. If a filter needs a different default behavior, it can override this method. The ExtractImageFilter overrides this function object so that if the input image is a higher dimension than the output image, the filter can control "where" in the input image the output subimage is extracted (as opposed to mapping to first few dimensions of the input).

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::ChooseMetric (  float  whichmetric  )

Choose the metric by parameter : 0= mean squares, 1=cross correlation, 2=pattern intensity, 3 = mutual information.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::ComputeJacobian (  float  sign = 1.0, FieldType *  field = NULL, float  smooth = 0.0 )

Compute the jacobian of the current deformation field.

virtual LightObject::Pointer itk::Object::CreateAnother (   )  const [virtual, inherited]

Create an object from an instance, potentially deferring to a factory. This method allows you to create an instance of an object that is exactly the same type as the referring object. This is useful in cases where an object has been cast back to a base class. Reimplemented from itk::LightObject.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::CreateLinearSystemSolver (   )  [protected]

Builds the itpack linear system wrapper with appropriate parameters. Currently undefined

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::CreateMesh (  double  ElementsPerSide, Solver &  S, ImageSizeType  sz )  [protected]

This function generates a regular mesh of ElementsPerSide^D size

virtual void itk::Object::DebugOff (   )  const [virtual, inherited]

Turn debugging output off.

virtual void itk::Object::DebugOn (   )  const [virtual, inherited]

Turn debugging output on.

virtual void itk::LightObject::Delete (   )  [virtual, inherited]

Delete an itk object. This method should always be used to delete an object when the new operator was used to create it. Using the C delete method will not work with reference counting.

template<class TMovingImage, class TFixedImage> The metric region allows one to compute the itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::derivative (  force   )

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::DoLineSearch (  unsigned int  b  )  [inline]

Finds the minimum energy between the current and next solution by linear search. Definition at line 341 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::DoMultiRes (  bool  b  )  [inline]

Sets the use of multi-resolution strategy. The control file always uses multi-res. Definition at line 345 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::EmployRegridding (  unsigned int  b  )  [inline]

Sets the use of multi-resolution strategy. The control file always uses multi-res. Definition at line 348 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::EnforceDiffeomorphism (  float  thresh, SolverType &  S, bool  onlywriteimages )

We check the jacobian of the current deformation field. If it is < threshold, we begin diffeomorphism enforcement: 1) Warp the moving image. 2) Set the vector field to zero. 3) Set the warped moving image as the new moving image, resizing if necessary.

virtual void itk::ProcessObject::EnlargeOutputRequestedRegion (  DataObject *   )  [inline, virtual, inherited]

Give the process object a chance to indictate that it will produce more output than it was requested to produce. For example, many imaging filters must compute the entire output at once or can only produce output in complete slices. Such filters cannot handle smaller requested regions. These filters must provide an implementation of this method, setting the output requested region to the size they will produce. By default, a process object does not modify the size of the output requested region. Reimplemented in itk::CurvatureFlowImageFilter< TInputImage, TOutputImage >, itk::ExtensionVelocitiesImageFilter< TLevelSet, TAuxValue, VAuxDimension >, itk::FastMarchingExtensionImageFilter< TLevelSet, TAuxValue, VAuxDimension, TSpeedImage >, itk::FastMarchingImageFilter< TLevelSet, TSpeedImage >, itk::ImagePCAShapeModelEstimator< TInputImage, TOutputImage >, itk::IsoContourDistanceImageFilter< TInputImage, TOutputImage >, itk::IsolatedWatershedImageFilter< TInputImage, TOutputImage >, itk::KLMRegionGrowImageFilter< TInputImage, TOutputImage >, itk::MRFImageFilter< TInputImage, TClassifiedImage >, itk::MultiResolutionPDEDeformableRegistration< TFixedImage, TMovingImage, TDeformationField >, itk::ReinitializeLevelSetImageFilter< TLevelSet >, itk::VoronoiSegmentationImageFilterBase< TInputImage, TOutputImage, TBinaryPriorImage >, itk::WatershedImageFilter< TInputImage >, itk::BlackTopHatImageFilter< TInputImage, TOutputImage, TKernel >, itk::BSplineDecompositionImageFilter< TInputImage, TOutputImage >, itk::ClosingByReconstructionImageFilter< TInputImage, TOutputImage, TKernel >, itk::ConfidenceConnectedImageFilter< TInputImage, TOutputImage >, itk::ConnectedComponentImageFilter< TInputImage, TOutputImage, TMaskImage >, itk::ConnectedThresholdImageFilter< TInputImage, TOutputImage >, itk::ContourDirectedMeanDistanceImageFilter< TInputImage1, TInputImage2 >, itk::ContourMeanDistanceImageFilter< TInputImage1, TInputImage2 >, itk::DirectedHausdorffDistanceImageFilter< TInputImage1, TInputImage2 >, itk::DoubleThresholdImageFilter< TInputImage, TOutputImage >, itk::ExtractOrthogonalSwath2DImageFilter< TImage >, itk::GradientMagnitudeRecursiveGaussianImageFilter< TInputImage, TOutputImage >, itk::GradientRecursiveGaussianImageFilter< TInputImage, TOutputImage >, itk::GrayscaleConnectedClosingImageFilter< TInputImage, TOutputImage >, itk::GrayscaleConnectedOpeningImageFilter< TInputImage, TOutputImage >, itk::GrayscaleFillholeImageFilter< TInputImage, TOutputImage >, itk::GrayscaleGeodesicDilateImageFilter< TInputImage, TOutputImage >, itk::GrayscaleGeodesicErodeImageFilter< TInputImage, TOutputImage >, itk::GrayscaleGrindPeakImageFilter< TInputImage, TOutputImage >, itk::GrayscaleMorphologicalClosingImageFilter< TInputImage, TOutputImage, TKernel >, itk::GrayscaleMorphologicalOpeningImageFilter< TInputImage, TOutputImage, TKernel >, itk::HausdorffDistanceImageFilter< TInputImage1, TInputImage2 >, itk::HConcaveImageFilter< TInputImage, TOutputImage >, itk::HConvexImageFilter< TInputImage, TOutputImage >, itk::HessianRecursiveGaussianImageFilter< TInputImage, TOutputImage >, itk::HMaximaImageFilter< TInputImage, TOutputImage >, itk::HMinimaImageFilter< TInputImage, TOutputImage >, itk::HoughTransform2DCirclesImageFilter< TInputPixelType, TOutputPixelType >, itk::HoughTransform2DLinesImageFilter< TInputPixelType, TOutputPixelType >, itk::ImportImageFilter< TPixel, VImageDimension >, itk::IsolatedConnectedImageFilter< TInputImage, TOutputImage >, itk::LabelStatisticsImageFilter< TInputImage, TLabelImage >, itk::LaplacianRecursiveGaussianImageFilter< TInputImage, TOutputImage >, itk::MinimumMaximumImageFilter< TInputImage >, itk::NeighborhoodConnectedImageFilter< TInputImage, TOutputImage >, itk::OpeningByReconstructionImageFilter< TInputImage, TOutputImage, TKernel >, itk::OrientImageFilter< TInputImage, TOutputImage >, itk::ReconstructionByDilationImageFilter< TInputImage, TOutputImage >, itk::ReconstructionByErosionImageFilter< TInputImage, TOutputImage >, itk::RecursiveSeparableImageFilter< TInputImage, TOutputImage >, itk::RegionOfInterestImageFilter< TInputImage, TOutputImage >, itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >, itk::SmoothingRecursiveGaussianImageFilter< TInputImage, TOutputImage >, itk::StatisticsImageFilter< TInputImage >, itk::TobogganImageFilter< TInputImage >, itk::VectorConfidenceConnectedImageFilter< TInputImage, TOutputImage >, itk::WhiteTopHatImageFilter< TInputImage, TOutputImage, TKernel >, itk::ImageFileReader< TOutputImage, ConvertPixelTraits >, itk::ImageSeriesReader< TOutputImage >, and itk::VoronoiSegmentationImageFilterBase< TInputImage, TOutputImage >. Definition at line 222 of file itkProcessObject.h.

template<class TMovingImage, class TFixedImage> Float itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::EvaluateEnergy (   )  [protected]

Evaluates the image similarity energy by calling the image metric

template<class TMovingImage, class TFixedImage> Float itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::EvaluateResidual (  SolverType &  mySolver, Float  t )  [protected]

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::FindBracketingTriplet (  SolverType &  mySolver, Float *  a, Float *  b, Float *  c )  [protected]

virtual void itk::ImageSource< TFixedImage >::GenerateData (  void   )  [protected, virtual, inherited]

A version of GenerateData() specific for image processing filters. This implementation will split the processing across multiple threads. The buffer is allocated by this method. Then the BeforeThreadedGenerateData() method is called (if provided). Then, a series of threads are spawned each calling ThreadedGenerateData(). After all the threads have completed processing, the AfterThreadedGenerateData() method is called (if provided). If an image processing filter cannot be threaded, the filter should provide an implementation of GenerateData(). That implementation is responsible for allocating the output buffer. If a filter an be threaded, it should NOT provide a GenerateData() method but should provide a ThreadedGenerateData() instead. See also: ThreadedGenerateData() Reimplemented from itk::ProcessObject.

virtual void itk::ImageToImageFilter< TMovingImage , TFixedImage >::GenerateInputRequestedRegion (   )  [protected, virtual, inherited]

What is the input requested region that is required to produce the output requested region? The base assumption for image processing filters is that the input requested region can be set to match the output requested region. If a filter requires more input (for instance a filter that uses neighborhoods needs more input than output to avoid introducing artificial boundary conditions) or less input (for instance a magnify filter) will have to override this method. In doing so, it should call its superclass' implementation as its first step. Note that imaging filters operate differently than the classes to this point in the class hierachy. Up till now, the base assumption has been that the largest possible region will be requested of the input. This implementation of GenerateInputRequestedRegion() only processes the inputs that are a subclass of the ImageBase<InputImageDimension>. If an input is another type of DataObject (including an Image of a different dimension), they are skipped by this method. The subclasses of ImageToImageFilter are responsible for providing an implementation of GenerateInputRequestedRegion() when there are multiple inputs of different types. See also: ProcessObject::GenerateInputRequestedRegion(), ImageSource::GenerateInputRequestedRegion() Reimplemented from itk::ProcessObject.

virtual void itk::ProcessObject::GenerateOutputInformation (   )  [protected, virtual, inherited]

Generate the information decribing the output data. The default implementation of this method will copy information from the input to the output. A filter may override this method if its output will have different information than its input. For instance, a filter that shrinks an image will need to provide an implementation for this method that changes the spacing of the pixels. Such filters should call their superclass' implementation of this method prior to changing the information values they need (i.e. GenerateOutputInformation() should call Superclass::GenerateOutputInformation() prior to changing the information. Reimplemented in itk::BayesianClassifierInitializationImageFilter< TInputImage, TProbabilityPrecisionType >, itk::BinaryMask3DMeshSource< TInputImage, TOutputMesh >, itk::FastMarchingExtensionImageFilter< TLevelSet, TAuxValue, VAuxDimension, TSpeedImage >, itk::FastMarchingImageFilter< TLevelSet, TSpeedImage >, itk::FFTComplexConjugateToRealImageFilter< TPixel, Dimension >, itk::FFTRealToComplexConjugateImageFilter< TPixel, Dimension >, itk::MRFImageFilter< TInputImage, TClassifiedImage >, itk::MultiResolutionPDEDeformableRegistration< TFixedImage, TMovingImage, TDeformationField >, itk::MultiResolutionPyramidImageFilter< TInputImage, TOutputImage >, itk::PDEDeformableRegistrationFilter< TFixedImage, TMovingImage, TDeformationField >, itk::VoronoiDiagram2DGenerator< TCoordType >, itk::AccumulateImageFilter< TInputImage, TOutputImage >, itk::BinaryMaskToNarrowBandPointSetFilter< TInputImage, TOutputMesh >, itk::ChangeInformationImageFilter< TInputImage >, itk::CropImageFilter< TInputImage, TOutputImage >, itk::DeformationFieldSource< TOutputImage >, itk::ExpandImageFilter< TInputImage, TOutputImage >, itk::ExtractImageFilter< TInputImage, TOutputImage >, itk::ExtractOrthogonalSwath2DImageFilter< TImage >, itk::FlipImageFilter< TImage >, itk::GaussianImageSource< TOutputImage >, itk::GradientImageToBloxBoundaryPointImageFilter< TInputImage >, itk::HoughTransform2DLinesImageFilter< TInputPixelType, TOutputPixelType >, itk::ImageToMeshFilter< TInputImage, TOutputMesh >, itk::ImageToParametricSpaceFilter< TInputImage, TOutputMesh >, itk::ImportImageFilter< TPixel, VImageDimension >, itk::InterpolateImagePointsFilter< TInputImage, TOutputImage, TCoordType, InterpolatorType >, itk::InverseDeformationFieldImageFilter< TInputImage, TOutputImage >, itk::JoinSeriesImageFilter< TInputImage, TOutputImage >, itk::NonThreadedShrinkImageFilter< TInputImage, TOutputImage >, itk::OrientImageFilter< TInputImage, TOutputImage >, itk::PadImageFilter< TInputImage, TOutputImage >, itk::ParametricSpaceToImageSpaceMeshFilter< TInputMesh, TOutputMesh >, itk::PathToImageFilter< TInputPath, TOutputImage >, itk::PermuteAxesImageFilter< TImage >, itk::PointSetToImageFilter< TInputPointSet, TOutputImage >, itk::RandomImageSource< TOutputImage >, itk::RegionOfInterestImageFilter< TInputImage, TOutputImage >, itk::ResampleImageFilter< TInputImage, TOutputImage, TInterpolatorPrecisionType >, itk::ShrinkImageFilter< TInputImage, TOutputImage >, itk::SpatialObjectToImageFilter< TInputSpatialObject, TOutputImage >, itk::SpatialObjectToPointSetFilter< TInputSpatialObject, TOutputPointSet >, itk::TileImageFilter< TInputImage, TOutputImage >, itk::TriangleMeshToBinaryImageFilter, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, TFunction >, itk::VectorExpandImageFilter< TInputImage, TOutputImage >, itk::VectorResampleImageFilter< TInputImage, TOutputImage, TInterpolatorPrecisionType >, itk::VTKImageImport< TOutputImage >, itk::WarpImageFilter< TInputImage, TOutputImage, TDeformationField >, itk::WarpVectorImageFilter< TInputImage, TOutputImage, TDeformationField >, itk::ImageFileReader< TOutputImage, ConvertPixelTraits >, itk::ImageSeriesReader< TOutputImage >, itk::HistogramToImageFilter< THistogram, TFunction >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::Atan< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::Cos< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::Acos< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::InvertIntensityTransform< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::ChangeLabel< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< FeatureImageType, ImageType, Functor::Cast< FeatureImageType::PixelType, ImageType::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Function::Log< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Function::Abs< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Function::Exp< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Function::ComplexToReal< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::Cast< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::BoundedReciprocal< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Function::Sigmoid< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::VectorCast< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::VectorMagnitudeLinearTransform< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::IntensityLinearTransform< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Function::ComplexToModulus< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::IntensityWindowingTransform< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::NOT< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Function::Tan< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Function::ExpNegative< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Function::ComplexToPhase< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::ThresholdLabeler< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::SymmetricEigenAnalysisFunction< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Function::Sin< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Function::RGBToLuminance< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::TensorRelativeAnisotropyFunction< TInputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::MatrixIndexSelection< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Function::Sqrt< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::BinaryThreshold< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Function::Log10< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::AccessorFunctor< TInputImage::PixelType, TAccessor > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::ModulusTransform< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::TensorFractionalAnisotropyFunction< TInputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::Asin< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::EdgePotential< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Function::Square< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::VectorIndexSelectionCast< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Functor::GradientMagnitude< TInputImage::PixelType, TOutputImage::PixelType > >, itk::UnaryFunctorImageFilter< TInputImage, TOutputImage, Function::ComplexToImaginary< TInputImage::PixelType, TOutputImage::PixelType > >, itk::HistogramToImageFilter< THistogram, Function::HistogramEntropyFunction< unsigned long > >, itk::HistogramToImageFilter< THistogram, Function::HistogramLogProbabilityFunction< unsigned long > >, itk::HistogramToImageFilter< THistogram, Function::HistogramProbabilityFunction< unsigned long > >, and itk::HistogramToImageFilter< THistogram, Function::HistogramIntensityFunction< unsigned long > >.

virtual void itk::ProcessObject::GenerateOutputRequestedRegion (  DataObject *  output  )  [protected, virtual, inherited]

Given one output whose requested region has been set, how should the requested regions for the remaining outputs of the process object be set? By default, all the outputs are set to the same requested region. If a filter needs to produce different requested regions for each output, for instance an image processing filter producing several outputs at different resolutions, then that filter may override this method and set the requested regions appropriatedly. Note that a filter producing multiple outputs of different types is required to override this method. The default implementation can only correctly handle multiple outputs of the same type. Reimplemented in itk::MultiResolutionPyramidImageFilter< TInputImage, TOutputImage >, itk::RecursiveMultiResolutionPyramidImageFilter< TInputImage, TOutputImage >, itk::watershed::BoundaryResolver< TPixelType, TDimension >, itk::watershed::EquivalenceRelabeler< TScalarType, TImageDimension >, itk::watershed::Relabeler< TScalarType, TImageDimension >, itk::watershed::Segmenter< TInputImage >, itk::watershed::SegmentTreeGenerator< TScalarType >, itk::watershed::Relabeler< ScalarType, itkGetStaticConstMacro(ImageDimension)>, and itk::watershed::SegmentTreeGenerator< ScalarType >.

virtual const bool& itk::ProcessObject::GetAbortGenerateData (   )  [virtual, inherited]

Get the AbortGenerateData flag for the process object. Process objects may handle premature termination of execution in different ways.

Command* itk::Object::GetCommand (  unsigned long  tag  )  [inherited]

Get the command associated with the given tag. NOTE: This returns a pointer to a Command, but it is safe to asign this to a Command::Pointer. Since Command inherits from LightObject, at this point in the code, only a pointer or a reference to the Command can be used.

template<class TMovingImage, class TFixedImage> std::string itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::GetConfigFileName (   )  [inline]

Definition at line 363 of file itkFEMRegistrationFilter.h.

bool itk::Object::GetDebug (   )  const [inherited]

Get the value of the debug flag.

template<class TMovingImage, class TFixedImage> FieldType* itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::GetDeformationField (   )  [inline]

Outputs the FE deformation field interpolated over the entire image domain. Definition at line 241 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> Float itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::GetElasticity (  unsigned int  which = 0  )  [inline]

Gets the stiffness Matrix weight. Definition at line 326 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> std::string itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::GetFixedFile (   )  [inline]

Definition at line 212 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> FixedImageType* itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::GetFixedImage (   )  [inline]

Definition at line 226 of file itkFEMRegistrationFilter.h.

static bool itk::Object::GetGlobalWarningDisplay (   )  [static, inherited]

template<class TMovingImage, class TFixedImage> ImageSizeType itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::GetImageSize (   )  [inline]

Definition at line 365 of file itkFEMRegistrationFilter.h.

const DataObject* itk::ProcessObject::GetInput (  unsigned int  idx  )  const [protected, inherited]

const InputImageType* itk::ImageToImageFilter< TMovingImage , TFixedImage >::GetInput (  unsigned int  idx  )  [inherited]

Reimplemented from itk::ProcessObject.

const InputImageType* itk::ImageToImageFilter< TMovingImage , TFixedImage >::GetInput (  void   )  [inherited]

DataObjectPointerArray& itk::ProcessObject::GetInputs (   )  [inline, inherited]

Return an array with all the inputs of this process object. This is useful for tracing back in the pipeline to construct graphs etc. Definition at line 108 of file itkProcessObject.h.

template<class TMovingImage, class TFixedImage> virtual InterpolatorType* itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::GetInterpolator (   )  [virtual]

Get a pointer to the interpolator function.

template<class TMovingImage, class TFixedImage> FloatImageType* itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::GetJacobianImage (   )  [inline]

Get the image that gives the jacobian of the deformation field. Definition at line 237 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> Set the solver s current load* virtual ImageMetricLoadType* itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::GetLoad (   )  [protected, virtual]

const MetaDataDictionary& itk::Object::GetMetaDataDictionary (  void   )  const [inherited]

Returns: A constant reference to this objects MetaDataDictionary.

MetaDataDictionary& itk::Object::GetMetaDataDictionary (  void   )  [inherited]

Returns: A reference to this objects MetaDataDictionary. Warning: This reference may be changed.

template<class TMovingImage, class TFixedImage> Set Get the Metric* MetricBaseTypePointer itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::GetMetric (   )  [inline]

Definition at line 368 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> FloatImageType* itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::GetMetricImage (  FieldType *  F  )  [protected]

Calculates the metric over the domain given the vector field.

template<class TMovingImage, class TFixedImage> std::string itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::GetMovingFile (   )  [inline]

Definition at line 208 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> MovingImageType* itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::GetMovingImage (   )  [inline]

Definition at line 223 of file itkFEMRegistrationFilter.h.

virtual unsigned long itk::Object::GetMTime (   )  const [virtual, inherited]

Return this objects modified time. Reimplemented in itk::ImageRegistrationMethod< TFixedImage, TMovingImage >, itk::DeformationFieldSource< TOutputImage >, itk::InverseDeformationFieldImageFilter< TInputImage, TOutputImage >, itk::ResampleImageFilter< TInputImage, TOutputImage, TInterpolatorPrecisionType >, itk::VectorResampleImageFilter< TInputImage, TOutputImage, TInterpolatorPrecisionType >, itk::BoundingBox< TPointIdentifier, VPointDimension, TCoordRep, TPointsContainer >, itk::SceneSpatialObject< SpaceDimension >, and itk::SceneSpatialObject< NDimensions >.

MultiThreader* itk::ProcessObject::GetMultiThreader (   )  [inline, inherited]

Return the multithreader used by this class. Definition at line 281 of file itkProcessObject.h.

template<class TMovingImage, class TFixedImage> virtual const char* itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::GetNameOfClass (   )  const [virtual]

Run-time type information (and related methods) Reimplemented from itk::ImageToImageFilter< TMovingImage, TFixedImage >.

std::vector<DataObjectPointer>::size_type itk::ProcessObject::GetNumberOfInputs (   )  const [inline, inherited]

Get the size of the input vector. This is merely the size of the input vector, not the number of inputs that have valid DataObject's assigned. Use GetNumberOfValidRequiredInputs() to determine how many inputs are non-null. Definition at line 115 of file itkProcessObject.h.

std::vector<DataObjectPointer>::size_type itk::ProcessObject::GetNumberOfOutputs (   )  const [inline, inherited]

Definition at line 132 of file itkProcessObject.h.

virtual const unsigned int& itk::ProcessObject::GetNumberOfRequiredInputs (   )  [protected, virtual, inherited]

virtual const unsigned int& itk::ProcessObject::GetNumberOfRequiredOutputs (   )  [protected, virtual, inherited]

virtual const int& itk::ProcessObject::GetNumberOfThreads (   )  [virtual, inherited]

virtual std::vector<DataObjectPointer>::size_type itk::ProcessObject::GetNumberOfValidRequiredInputs (   )  const [virtual, inherited]

Get the number of valid inputs. This is the number of non-null entries in the input vector in the first NumberOfRequiredInputs slots. This method is used to determine whether the necessary required inputs have been set. Subclasses of ProcessObject may override this implementation if the required inputs are not the first slots in input vector. Reimplemented in itk::MultiResolutionPDEDeformableRegistration< TFixedImage, TMovingImage, TDeformationField >, and itk::PDEDeformableRegistrationFilter< TFixedImage, TMovingImage, TDeformationField >.

template<class TMovingImage, class TFixedImage> MovingImageType* itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::GetOriginalMovingImage (   )  [inline]

Definition at line 224 of file itkFEMRegistrationFilter.h.

const DataObject* itk::ProcessObject::GetOutput (  unsigned int  idx  )  const [protected, inherited]

OutputImageType* itk::ImageSource< TFixedImage >::GetOutput (  unsigned int  idx  )  [inherited]

Reimplemented from itk::ProcessObject.

Get the output data of this process object The output of this* function is not valid until an appropriate either explicitly or implicitly Both the filter* itself and the data object have and both* methods update the data Here are three ways to use* itk::ImageSource< TFixedImage >::GetOutput (  void   )  [inherited]

Return an array with all the outputs of this process object* This is useful for tracing forward in the pipeline to contruct* graphs etc* DataObjectPointerArray& itk::ProcessObject::GetOutputs (   )  [inline, inherited]

Definition at line 130 of file itkProcessObject.h.

virtual const float& itk::ProcessObject::GetProgress (   )  [virtual, inherited]

Get the execution progress of a process object. The progress is a floating number in [0,1] with 0 meaning no progress and 1 meaning the filter has completed execution.

virtual int itk::LightObject::GetReferenceCount (   )  const [inline, virtual, inherited]

Gets the reference count on this object. Definition at line 98 of file itkLightObject.h.

virtual const bool& itk::ProcessObject::GetReleaseDataBeforeUpdateFlag (   )  [virtual, inherited]

virtual bool itk::ProcessObject::GetReleaseDataFlag (   )  const [virtual, inherited]

template<class TMovingImage, class TFixedImage> std::string itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::GetResultsFileName (   )  [inline]

Definition at line 277 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> FixedImageType* itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::GetWarpedImage (   )  [inline]

Get the reference image warped to the target image. Must first apply the warp using WarpImage() Definition at line 231 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> unsigned int itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::GetWidthOfMetricRegion (  unsigned int  which = 0  )  [inline]

Definition at line 302 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> bool itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::GetWriteDisplacements (   )  [inline]

Sets the boolean for writing the displacement field to a file. Definition at line 357 of file itkFEMRegistrationFilter.h.

static void itk::Object::GlobalWarningDisplayOff (   )  [inline, static, inherited]

Definition at line 100 of file itkObject.h. References itk::Object::SetGlobalWarningDisplay().

static void itk::Object::GlobalWarningDisplayOn (   )  [inline, static, inherited]

Definition at line 98 of file itkObject.h. References itk::Object::SetGlobalWarningDisplay().

template<class TMovingImage, class TFixedImage> Float itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::GoldenSection (  SolverType &  mySolver, Float  tol = 0.01, unsigned int  MaxIters = 25 )  [protected]

Finds the optimum value between the last two solutions and sets the current solution to that value. Uses Evaluate Residual;

virtual void itk::ImageSource< TFixedImage >::GraftNthOutput (  unsigned int  idx, DataObject *  output )  [virtual, inherited]

Graft the specified data object onto this ProcessObject's idx'th output. This is the similar to GraftOutput method except is allows you specify which output is affected. The specified index must be a valid output number (less than ProcessObject::GetNumberOfOutputs()). See the GraftOutput for general usage information.

virtual void itk::ImageSource< TFixedImage >::GraftOutput (  DataObject *  output  )  [virtual, inherited]

Graft the specified DataObject onto this ProcessObject's output. This method grabs a handle to the specified DataObject's bulk data to used as its output's own bulk data. It also copies the region ivars (RequestedRegion, BufferedRegion, LargestPossibleRegion) and meta-data (Spacing, Origin) from the specified data object into this filter's output data object. Most importantly, however, it leaves the Source ivar untouched so the original pipeline routing is intact. This method is used when a process object is implemented using a mini-pipeline which is defined in its GenerateData() method. The usage is: // setup the mini-pipeline to process the input to this filter firstFilterInMiniPipeline->SetInput( this->GetInput() ); // setup the mini-pipeline to calculate the correct regions // and write to the appropriate bulk data block lastFilterInMiniPipeline->GraftOutput( this->GetOutput() ); // execute the mini-pipeline lastFilterInMiniPipeline->Update(); // graft the mini-pipeline output back onto this filter's output. // this is needed to get the appropriate regions passed back. this->GraftOutput( lastFilterInMiniPipeline->GetOutput() ); For proper pipeline execution, a filter using a mini-pipeline must implement the GenerateInputRequestedRegion(), GenerateOutputRequestedRegion(), GenerateOutputInformation() and EnlargeOutputRequestedRegion() methods as necessary to reflect how the mini-pipeline will execute (in other words, the outer filter's pipeline mechanism must be consistent with what the mini-pipeline will do).

bool itk::Object::HasObserver (  const EventObject &  event  )  const [inherited]

Return true if an observer is registered for this event.

Get the output data of this process object The output of this* function is not valid until an appropriate either explicitly or implicitly Both the filter* itself and the data object have and both* methods update the data Here are three ways to use* a image is a pointer to some Image and the* particular ProcessObjects involved are filters The same* examples apply to non itk::ImageSource< TFixedImage >::image (  e.g.  Mesh  )  [inherited]

itk::ImageSource< TFixedImage >::ImageSource (   )  [protected, inherited]

itk::ImageToImageFilter< TMovingImage , TFixedImage >::ImageToImageFilter (   )  [protected, inherited]

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::InterpolateVectorField (  SolverType &  S  )  [protected]

Interpolates the vector field over the domain. Our convention is to always keep the vector field at the scale of the original images.

void itk::Object::InvokeEvent (  const EventObject &   )  const [inherited]

Call Execute on all the Commands observing this event id. The actions triggered by this call doesn't modify this object.

void itk::Object::InvokeEvent (  const EventObject &   )  [inherited]

Call Execute on all the Commands observing this event id.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::IterativeSolve (  SolverType &  S  )

The solution loop

itk::ImageToImageFilter< TMovingImage , TFixedImage >::itkStaticConstMacro (  OutputImageDimension  , unsigned  int, TFixedImage ::ImageDimension  )  [inherited]

ImageDimension constants* itk::ImageToImageFilter< TMovingImage , TFixedImage >::itkStaticConstMacro (  InputImageDimension  , unsigned  int, TMovingImage ::ImageDimension  )  [inherited]

template<class TMovingImage, class TFixedImage> itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::itkStaticConstMacro (  ImageDimension  , unsigned  int, FixedImageType::ImageDimension  )

Dimensionality of input and output data is assumed to be the same.

virtual DataObjectPointer itk::ImageSource< TFixedImage >::MakeOutput (  unsigned int  idx  )  [virtual, inherited]

Make a DataObject of the correct type to used as the specified output. Every ProcessObject subclass must be able to create a DataObject that can be used as a specified output. This method is automatically called when DataObject::DisconnectPipeline() is called. DataObject::DisconnectPipeline, disconnects a data object from being an output of its current source. When the data object is disconnected, the ProcessObject needs to construct a replacement output data object so that the ProcessObject is in a valid state. So DataObject::DisconnectPipeline eventually calls ProcessObject::MakeOutput. Note that MakeOutput always returns a SmartPointer to a DataObject. If a subclass of ImageSource has multiple outputs of different types, then that class must provide an implementation of MakeOutput(). Reimplemented from itk::ProcessObject.

virtual void itk::Object::Modified (   )  const [virtual, inherited]

Update the modification time for this object. Many filters rely on the modification time to determine if they need to recompute their data. Referenced by itk::MatrixOffsetTransformBase< TScalarType, 3, 3 >::SetCenter(), itk::HistogramAlgorithmBase< TInputHistogram >::SetInputHistogram(), itk::MatrixOffsetTransformBase< TScalarType, 3, 3 >::SetMatrix(), itk::MatrixOffsetTransformBase< TScalarType, 3, 3 >::SetOffset(), itk::ThresholdLabelerImageFilter< TInputImage, TOutputImage >::SetRealThresholds(), itk::CollidingFrontsImageFilter< TInputImage, TOutputImage >::SetSeedPoints1(), itk::CollidingFrontsImageFilter< TInputImage, TOutputImage >::SetSeedPoints2(), itk::NonUniformBSpline< TDimension >::SetSplineOrder(), itk::ThresholdLabelerImageFilter< TInputImage, TOutputImage >::SetThresholds(), itk::Statistics::GoodnessOfFitFunctionBase< typename ComponentType::HistogramType >::SetTotalObservedScale(), and itk::MatrixOffsetTransformBase< TScalarType, 3, 3 >::SetTranslation().

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::MultiResSolve (   )

The solution loop for a simple multi-resolution strategy.

template<class TMovingImage, class TFixedImage> static Pointer itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::New (   )  [static]

Method for creation through the object factory. Reimplemented from itk::Object.

virtual void itk::ImageToImageFilter< TMovingImage , TFixedImage >::PopBackInput (   )  [virtual, inherited]

Reimplemented from itk::ProcessObject.

virtual void itk::ImageToImageFilter< TMovingImage , TFixedImage >::PopFrontInput (   )  [virtual, inherited]

Reimplemented from itk::ProcessObject.

virtual void itk::ProcessObject::PrepareOutputs (   )  [virtual, inherited]

An opportunity to deallocate a ProcessObject's bulk data storage. Some filters may wish to reuse existing bulk data storage to avoid unnecessary deallocation/allocation sequences. The default implementation calls Initialize() on each output. DataObject::Initialize() frees its bulk data by default. Reimplemented in itk::WatershedImageFilter< TInputImage >.

void itk::LightObject::Print (  std::ostream &  os, Indent  indent = 0 )  const [inherited]

Cause the object to print itself out.

bool itk::Object::PrintObservers (  std::ostream &  os, Indent  indent )  const [protected, inherited]

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::PrintSelf (  std::ostream &  os, Indent  indent )  const [protected, virtual]

Methods invoked by Print() to print information about the object including superclasses. Typically not called by the user (use Print() instead) but used in the hierarchical print process to combine the output of several classes. Reimplemented from itk::ImageToImageFilter< TMovingImage, TFixedImage >.

virtual void itk::LightObject::PrintTrailer (  std::ostream &  os, Indent  indent )  const [protected, virtual, inherited]

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::PrintVectorField (  unsigned int  modnum = 1000  )

virtual void itk::ProcessObject::PropagateRequestedRegion (  DataObject *  output  )  [virtual, inherited]

Send the requested region information back up the pipeline (to the filters that preceed this one). Reimplemented in itk::VTKImageImport< TOutputImage >.

virtual void itk::ProcessObject::PropagateResetPipeline (   )  [protected, virtual, inherited]

Propagate a call to ResetPipeline() up the pipeline. Called only from DataObject.

* * these methods end of hiding the versions from the superclass* ProcessObject whose arguments are DataObjects we re expose* the versions from ProcessObject to avoid warnings about hiding* methods from the superclass* void itk::ImageToImageFilter< TMovingImage , TFixedImage >::PushBackInput (  const DataObject *  input  )  [inline, protected, virtual, inherited]

Reimplemented from itk::ProcessObject. Definition at line 250 of file itkImageToImageFilter.h.

* itk::ImageToImageFilter< TMovingImage , TFixedImage >::PushBackInput (   )  [protected, inherited]

Push Pop the input of this process object These methods allow a* filter to model its input vector as a queue or stack These* routines may not be appropriate for all especially* filters with different types of inputs These routines follow* the semantics of STL* * The routines are useful for applications that need to process* rolling sets of images For if an application has* images and they need to run a filter on then* run the filter on then run the filter on the application can accomplish this by popping* an input off the front of the input list and push a new image* onto the back of input list this only makes sense for* filters that single type of input* * Other uses are also possible For a single input pushing* and popping inputs allow the application to temporarily replace* an input to a filter** virtual void itk::ImageToImageFilter< TMovingImage , TFixedImage >::PushBackInput (  const InputImageType *  image  )  [virtual, inherited]

* itk::ImageToImageFilter< TMovingImage , TFixedImage >::PushFronInput (   )  [protected, inherited]

void itk::ImageToImageFilter< TMovingImage , TFixedImage >::PushFrontInput (  const DataObject *  input  )  [inline, protected, virtual, inherited]

Reimplemented from itk::ProcessObject. Definition at line 252 of file itkImageToImageFilter.h.

virtual void itk::ImageToImageFilter< TMovingImage , TFixedImage >::PushFrontInput (  const InputImageType *  image  )  [virtual, inherited]

template<class TMovingImage, class TFixedImage> bool itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::ReadConfigFile (  const char *   )

Read the configuration file to set up the example parameters

virtual void itk::Object::Register (   )  const [virtual, inherited]

Increase the reference count (mark as used by another object). Reimplemented from itk::LightObject.

virtual void itk::ProcessObject::ReleaseDataBeforeUpdateFlagOff (   )  [virtual, inherited]

virtual void itk::ProcessObject::ReleaseDataBeforeUpdateFlagOn (   )  [virtual, inherited]

void itk::ProcessObject::ReleaseDataFlagOff (   )  [inline, inherited]

Definition at line 254 of file itkProcessObject.h.

void itk::ProcessObject::ReleaseDataFlagOn (   )  [inline, inherited]

Definition at line 253 of file itkProcessObject.h.

virtual void itk::ProcessObject::ReleaseInputs (   )  [protected, virtual, inherited]

A filter may need to release its input's bulk data after it has finished calculating a new output. The filter may need to release the inputs because the user has turned on the ReleaseDataFlag or it may need to release the inputs because the filter is an "in place" filter and it has overwritten its input with its output data. The implementation here simply checks the ReleaseDataFlag of the inputs. InPlaceImageFilter overrides this method so release the input it has overwritten. See also: InPlaceImageFilter::ReleaseInputs() Reimplemented in itk::InPlaceImageFilter< TInputImage, TOutputImage >, itk::InPlaceImageFilter< TInputImage, TOutputImage >, itk::InPlaceImageFilter< TDeformationField, TDeformationField >, itk::InPlaceImageFilter< TInputImage >, itk::InPlaceImageFilter< TInputImage, TSparseOutputImage >, itk::InPlaceImageFilter< TInputImage1, TOutputImage >, itk::InPlaceImageFilter< TInputImage, Image< TOutputPixelType,::itk::GetImageDimension< TInputImage >::ImageDimension > >, itk::InPlaceImageFilter< FeatureImageType, ImageType >, itk::InPlaceImageFilter< TInputImage1, Functor::MakeJoin< TInputImage1, TInputImage2 >::ImageType >, itk::InPlaceImageFilter< TInputImageType, TSparseOutputImageType >, and itk::InPlaceImageFilter< TImage, TImage >.

void itk::Object::RemoveAllObservers (   )  [inherited]

Remove all observers .

virtual void itk::ProcessObject::RemoveInput (  DataObject *  input  )  [protected, virtual, inherited]

void itk::Object::RemoveObserver (  unsigned long  tag  )  [inherited]

Remove the observer with this tag value.

virtual void itk::ProcessObject::RemoveOutput (  DataObject *  output  )  [protected, virtual, inherited]

virtual void itk::ProcessObject::ResetPipeline (   )  [virtual, inherited]

Reset the pipeline. If an exception is thrown during an Update(), the pipeline may be in an inconsistent state. This method clears the internal state of the pipeline so Update() can be called.

virtual void itk::ProcessObject::RestoreInputReleaseDataFlags (   )  [protected, virtual, inherited]

Restore the cached input ReleaseDataFlags.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::RunRegistration (  void   )

Call this to register two images.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SampleVectorFieldAtNodes (  SolverType &  S  )  [protected]

This is used for changing between mesh resolutions.

virtual void itk::ProcessObject::SetAbortGenerateData (  bool  _arg  )  [virtual, inherited]

Set the AbortGenerateData flag for the process object. Process objects may handle premature termination of execution in different ways.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetAlpha (  Float  a  )  [inline]

Set alpha for the trapezoidal rule (usually 1.0 in our experiments). Definition at line 316 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetConfigFileName (  const char *  f  )  [inline]

Sets the file name for the FEM multi-resolution registration. One can also set the parameters in code. Definition at line 361 of file itkFEMRegistrationFilter.h.

void itk::Object::SetDebug (  bool  debugFlag  )  const [inherited]

Set the value of the debug flag. A non-zero value turns debugging on.

template<class TMovingImage, class TFixedImage> Sets the FE deformation field* void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetDeformationField (  FieldType *  F  )  [inline]

Definition at line 244 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetDescentDirectionMaximize (   )  [inline]

Tries to maximize energy Definition at line 338 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetDescentDirectionMinimize (   )  [inline]

Tries to minimize energy Definition at line 335 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetDisplacementsFile (  const char *  r  )  [inline]

Sets the filename for the vector field component images. Definition at line 280 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetElasticity (  Float  i, unsigned int  which = 0 )  [inline]

Sets the stiffness Matrix weight. Definition at line 323 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetElement (  Element::Pointer  e  )  [inline]

This function allows one to set the element and its material externally. Definition at line 377 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetEnergyReductionFactor (  Float  i  )  [inline]

Sets the energy below which we decide the solution has converged. Definition at line 320 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetFixedFile (  const char *  t  )  [inline]

Definition at line 210 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetFixedImage (  FixedImageType *  T  )

Define the target (fixed) image.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetGamma (  Float  r, unsigned int  which = 0 )  [inline]

Image similarity energy weight Definition at line 332 of file itkFEMRegistrationFilter.h.

This is a global flag that controls whether any warning* or error messages are displayed* static void itk::Object::SetGlobalWarningDisplay (  bool  flag  )  [static, inherited]

Referenced by itk::Object::GlobalWarningDisplayOff(), and itk::Object::GlobalWarningDisplayOn().

virtual void itk::ImageToImageFilter< TMovingImage , TFixedImage >::SetInput (  unsigned  int, const TMovingImage *  image )  [virtual, inherited]

Set Get the image input of this process object* virtual void itk::ImageToImageFilter< TMovingImage , TFixedImage >::SetInput (  const InputImageType *  image  )  [virtual, inherited]

template<class TMovingImage, class TFixedImage> virtual void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetInterpolator (  InterpolatorType *  _arg  )  [virtual]

Set the interpolator function.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetLandmarkFile (  const char *  l  )  [inline]

These functions control the use of landmark constraints. Currently, landmarks must be read in from a file. Definition at line 253 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetLineSearchMaximumIterations (  unsigned int  f  )  [inline]

This sets the line search's max iterations. Definition at line 351 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetMaterial (  MaterialType::Pointer  m  )  [inline]

This sets the pointer to the material. Definition at line 380 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetMaximumIterations (  unsigned int  i, unsigned int  which )  [inline]

Setting the maximum iterations stops the solution after i iterations regardless of energy. Parameters: i  number of elements which  determines the resolution of the solution process the call is applied to. Definition at line 309 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetMaxLevel (  unsigned int  i  )  [inline]

Definition at line 385 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> * void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetMeshPixelsPerElementAtEachResolution (  unsigned int  i, unsigned int  which = 0 )  [inline]

Definition at line 288 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> The FEM filter can generate its own mesh for or if none is provided The mesh is generated for quadrilaterals in D and hexahedra in D This function sets the number of elements generated along each dimension at the resolution designated by which E g to generate pixels per element in each dimension in the st use itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetMeshResolution (  10  , 0  )

void itk::Object::SetMetaDataDictionary (  const MetaDataDictionary &  rhs  )  [inherited]

Returns: Set the MetaDataDictionary

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetMetric (  MetricBaseTypePointer  MP  )  [inline]

Definition at line 369 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetMovingFile (  const char *  r  )  [inline]

One can set the reference file names to read images from files Definition at line 206 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetMovingImage (  MovingImageType *  R  )

Define the reference (moving) image.

Protected methods for setting inputs* Subclasses make use of them for setting input* virtual void itk::ProcessObject::SetNthInput (  unsigned int  num, DataObject *  input )  [protected, virtual, inherited]

Referenced by itk::watershed::BoundaryResolver< TPixelType, TDimension >::SetBoundaryA(), itk::watershed::BoundaryResolver< TPixelType, TDimension >::SetBoundaryB(), itk::watershed::EquivalenceRelabeler< TScalarType, TImageDimension >::SetEquivalencyTable(), itk::WatershedImageFilter< TInputImage >::SetInput(), itk::watershed::SegmentTreeGenerator< ScalarType >::SetInputEquivalencyTable(), itk::watershed::Segmenter< TInputImage >::SetInputImage(), itk::watershed::Relabeler< ScalarType, itkGetStaticConstMacro(ImageDimension)>::SetInputImage(), itk::watershed::EquivalenceRelabeler< TScalarType, TImageDimension >::SetInputImage(), itk::watershed::SegmentTreeGenerator< ScalarType >::SetInputSegmentTable(), itk::watershed::Relabeler< ScalarType, itkGetStaticConstMacro(ImageDimension)>::SetInputSegmentTree(), itk::ResampleImageFilter< TInputImage, TOutputImage, TInterpolatorPrecisionType >::SetReferenceImage(), itk::DiffusionTensor3DReconstructionImageFilter< TReferenceImagePixelType, TGradientImagePixelType, TTensorPixelType >::SetReferenceImage(), and itk::ChangeInformationImageFilter< TInputImage >::SetReferenceImage().

Protected methods for setting outputs* Subclasses make use of them for getting output* virtual void itk::ProcessObject::SetNthOutput (  unsigned int  num, DataObject *  output )  [protected, virtual, inherited]

Referenced by itk::watershed::BoundaryResolver< TPixelType, TDimension >::BoundaryResolver(), itk::watershed::EquivalenceRelabeler< TScalarType, TImageDimension >::EquivalenceRelabeler(), itk::watershed::Segmenter< TInputImage >::SetBoundary(), itk::watershed::BoundaryResolver< TPixelType, TDimension >::SetEquivalencyTable(), itk::watershed::Segmenter< TInputImage >::SetOutputImage(), itk::watershed::Relabeler< ScalarType, itkGetStaticConstMacro(ImageDimension)>::SetOutputImage(), itk::watershed::EquivalenceRelabeler< TScalarType, TImageDimension >::SetOutputImage(), and itk::watershed::Segmenter< TInputImage >::SetSegmentTable().

void itk::ProcessObject::SetNumberOfInputs (  unsigned int  num  )  [protected, inherited]

Called to allocate the input array. Copies old inputs.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetNumberOfIntegrationPoints (  unsigned int  i, unsigned int  which = 0 )  [inline]

This determines the number of integration points to use at each resolution. These integration points are used to generate the force. The actual number used will be i^d, where d is the number of parameters in the elements local domain. Definition at line 294 of file itkFEMRegistrationFilter.h.

void itk::ProcessObject::SetNumberOfOutputs (  unsigned int  num  )  [protected, inherited]

Called to allocate the output array. Copies old outputs.

virtual void itk::ProcessObject::SetNumberOfRequiredInputs (  unsigned int  _arg  )  [protected, virtual, inherited]

virtual void itk::ProcessObject::SetNumberOfRequiredOutputs (  unsigned int  _arg  )  [protected, virtual, inherited]

Get Set the number of threads to create when executing* virtual void itk::ProcessObject::SetNumberOfThreads (  int  _arg  )  [virtual, inherited]

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetNumLevels (  unsigned int  i  )  [inline]

Definition at line 384 of file itkFEMRegistrationFilter.h.

virtual void itk::ProcessObject::SetProgress (  float  _arg  )  [virtual, inherited]

Set the execution progress of a process object. The progress is a floating number in [0,1] with 0 meaning no progress and 1 meaning the filter has completed execution. The ProgressEvent is NOT invoked.

virtual void itk::Object::SetReferenceCount (  int   )  [virtual, inherited]

Sets the reference count (use with care) Reimplemented from itk::LightObject.

Turn on off the flags to control whether the bulk data belonging* to the outputs of this ProcessObject are released after being* used by a downstream ProcessObject Default value is off Another* options for controlling memory utilization is the* ReleaseDataBeforeUpdateFlag* virtual void itk::ProcessObject::SetReleaseDataFlag (  bool  flag  )  [virtual, inherited]

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetResultsFile (  const char *  r  )  [inline]

The warped reference image will be written to this file name with the extension "11.img" appended to it. One can also output the image after every iteration, yielding result11.img, result12.img, etc. by uncommenting the code at the end of IterativeSolve. Definition at line 273 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetResultsFileName (  const char *  f  )  [inline]

Definition at line 275 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetRho (  Float  r, unsigned int  which = 0 )  [inline]

Mass matrix weight Definition at line 329 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetTemp (  Float  i  )  [inline]

Definition at line 387 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetTimeStep (  Float  i  )  [inline]

Setting the time step - usually 1.0. We prefer to use rho to control step sizes. Definition at line 313 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> The metric region allows one to compute the i in D [i,i,i] in D* param i number of elements* param which determines the region at a given resolution of the solution process* void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetWidthOfMetricRegion (  unsigned int  i, unsigned int  which = 0 )  [inline]

Definition at line 301 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::SetWriteDisplacements (  bool  b  )  [inline]

Sets the boolean for writing the displacement field to a file. Definition at line 354 of file itkFEMRegistrationFilter.h.

virtual int itk::ImageSource< TFixedImage >::SplitRequestedRegion (  int  i, int  num, OutputImageRegionType &  splitRegion )  [protected, virtual, inherited]

Split the output's RequestedRegion into "num" pieces, returning region "i" as "splitRegion". This method is called "num" times. The regions must not overlap. The method returns the number of pieces that the routine is capable of splitting the output RequestedRegion, i.e. return value is less than or equal to "num".

virtual void itk::ImageSource< TFixedImage >::ThreadedGenerateData (  const OutputImageRegionType &  outputRegionForThread, int  threadId )  [protected, virtual, inherited]

If an imaging filter can be implemented as a multithreaded algorithm, the filter will provide an implementation of ThreadedGenerateData(). This superclass will automatically split the output image into a number of pieces, spawn multiple threads, and call ThreadedGenerateData() in each thread. Prior to spawning threads, the BeforeThreadedGenerateData() method is called. After all the threads have completed, the AfterThreadedGenerateData() method is called. If an image processing filter cannot support threading, that filter should provide an implementation of the GenerateData() method instead of providing an implementation of ThreadedGenerateData(). If a filter provides a GenerateData() method as its implementation, then the filter is responsible for allocating the output data. If a filter provides a ThreadedGenerateData() method as its implementation, then the output memory will allocated automatically by this superclass. The ThreadedGenerateData() method should only produce the output specified by "outputThreadRegion" parameter. ThreadedGenerateData() cannot write to any other portion of the output image (as this is responsibility of a different thread). See also: GenerateData(), SplitRequestedRegion()

static ITK_THREAD_RETURN_TYPE itk::ImageSource< TFixedImage >::ThreaderCallback (  void *  arg  )  [static, protected, inherited]

Static function used as a "callback" by the MultiThreader. The threading library will call this routine for each thread, which will delegate the control to ThreadedGenerateData().

virtual void itk::Object::UnRegister (   )  const [virtual, inherited]

Decrease the reference count (release by another object). Reimplemented from itk::LightObject.

* endcode* In the above the two lines of code can be in* either order* * Note that it may be more efficient to* use a pipeline than to call itk::ImageSource< TFixedImage >::Update (   )  [virtual, inherited]

Bring this filter up-to-date. Update() checks modified times against last execution times, and re-executes objects if necessary. A side effect of this method is that the whole pipeline may execute in order to bring this filter up-to-date. This method updates the currently prescribed requested region. If no requested region has been set on the output, then the requested region will be set to the largest possible region. Once the requested region is set, Update() will make sure the specified requested region is up-to-date. This is a confusing side effect to users who are just calling Update() on a filter. A first call to Update() will cause the largest possible region to be updated. A second call to Update() will update that same region. If a modification to the upstream pipeline cause a filter to have a different largest possible region, this second call to Update() will not cause the output requested region to be reset to the new largest possible region. Instead, the output requested region will be the same as the last time Update() was called. To have a filter always to produce its largest possible region, users should call UpdateLargestPossibleRegion() instead. Reimplemented from itk::ProcessObject.

* endcode* In the above the two lines of code can be in* either order* * Note that itk::ImageSource< TFixedImage >::Update (   )  [virtual, inherited]

Bring this filter up-to-date. Update() checks modified times against last execution times, and re-executes objects if necessary. A side effect of this method is that the whole pipeline may execute in order to bring this filter up-to-date. This method updates the currently prescribed requested region. If no requested region has been set on the output, then the requested region will be set to the largest possible region. Once the requested region is set, Update() will make sure the specified requested region is up-to-date. This is a confusing side effect to users who are just calling Update() on a filter. A first call to Update() will cause the largest possible region to be updated. A second call to Update() will update that same region. If a modification to the upstream pipeline cause a filter to have a different largest possible region, this second call to Update() will not cause the output requested region to be reset to the new largest possible region. Instead, the output requested region will be the same as the last time Update() was called. To have a filter always to produce its largest possible region, users should call UpdateLargestPossibleRegion() instead. Reimplemented from itk::ProcessObject.

* endcode* * code* someFilter itk::ImageSource< TFixedImage >::Update (   )  [virtual, inherited]

Bring this filter up-to-date. Update() checks modified times against last execution times, and re-executes objects if necessary. A side effect of this method is that the whole pipeline may execute in order to bring this filter up-to-date. This method updates the currently prescribed requested region. If no requested region has been set on the output, then the requested region will be set to the largest possible region. Once the requested region is set, Update() will make sure the specified requested region is up-to-date. This is a confusing side effect to users who are just calling Update() on a filter. A first call to Update() will cause the largest possible region to be updated. A second call to Update() will update that same region. If a modification to the upstream pipeline cause a filter to have a different largest possible region, this second call to Update() will not cause the output requested region to be reset to the new largest possible region. Instead, the output requested region will be the same as the last time Update() was called. To have a filter always to produce its largest possible region, users should call UpdateLargestPossibleRegion() instead. Reimplemented from itk::ProcessObject.

* image itk::ImageSource< TFixedImage >::Update (   )  [virtual, inherited]

Bring this filter up-to-date. Update() checks modified times against last execution times, and re-executes objects if necessary. A side effect of this method is that the whole pipeline may execute in order to bring this filter up-to-date. This method updates the currently prescribed requested region. If no requested region has been set on the output, then the requested region will be set to the largest possible region. Once the requested region is set, Update() will make sure the specified requested region is up-to-date. This is a confusing side effect to users who are just calling Update() on a filter. A first call to Update() will cause the largest possible region to be updated. A second call to Update() will update that same region. If a modification to the upstream pipeline cause a filter to have a different largest possible region, this second call to Update() will not cause the output requested region to be reset to the new largest possible region. Instead, the output requested region will be the same as the last time Update() was called. To have a filter always to produce its largest possible region, users should call UpdateLargestPossibleRegion() instead. Reimplemented from itk::ProcessObject.

* anotherFilter itk::ImageSource< TFixedImage >::Update (   )  [virtual, inherited]

Bring this filter up-to-date. Update() checks modified times against last execution times, and re-executes objects if necessary. A side effect of this method is that the whole pipeline may execute in order to bring this filter up-to-date. This method updates the currently prescribed requested region. If no requested region has been set on the output, then the requested region will be set to the largest possible region. Once the requested region is set, Update() will make sure the specified requested region is up-to-date. This is a confusing side effect to users who are just calling Update() on a filter. A first call to Update() will cause the largest possible region to be updated. A second call to Update() will update that same region. If a modification to the upstream pipeline cause a filter to have a different largest possible region, this second call to Update() will not cause the output requested region to be reset to the new largest possible region. Instead, the output requested region will be the same as the last time Update() was called. To have a filter always to produce its largest possible region, users should call UpdateLargestPossibleRegion() instead. Reimplemented from itk::ProcessObject.

Get the output data of this process object The output of this* function is not valid until an appropriate either explicitly or implicitly Both the filter* itself and the data object have itk::ImageSource< TFixedImage >::Update (   )  [virtual, inherited]

Bring this filter up-to-date. Update() checks modified times against last execution times, and re-executes objects if necessary. A side effect of this method is that the whole pipeline may execute in order to bring this filter up-to-date. This method updates the currently prescribed requested region. If no requested region has been set on the output, then the requested region will be set to the largest possible region. Once the requested region is set, Update() will make sure the specified requested region is up-to-date. This is a confusing side effect to users who are just calling Update() on a filter. A first call to Update() will cause the largest possible region to be updated. A second call to Update() will update that same region. If a modification to the upstream pipeline cause a filter to have a different largest possible region, this second call to Update() will not cause the output requested region to be reset to the new largest possible region. Instead, the output requested region will be the same as the last time Update() was called. To have a filter always to produce its largest possible region, users should call UpdateLargestPossibleRegion() instead. Reimplemented from itk::ProcessObject.

Get the output data of this process object The output of this* function is not valid until an appropriate itk::ImageSource< TFixedImage >::Update (   )  [virtual, inherited]

Bring this filter up-to-date. Update() checks modified times against last execution times, and re-executes objects if necessary. A side effect of this method is that the whole pipeline may execute in order to bring this filter up-to-date. This method updates the currently prescribed requested region. If no requested region has been set on the output, then the requested region will be set to the largest possible region. Once the requested region is set, Update() will make sure the specified requested region is up-to-date. This is a confusing side effect to users who are just calling Update() on a filter. A first call to Update() will cause the largest possible region to be updated. A second call to Update() will update that same region. If a modification to the upstream pipeline cause a filter to have a different largest possible region, this second call to Update() will not cause the output requested region to be reset to the new largest possible region. Instead, the output requested region will be the same as the last time Update() was called. To have a filter always to produce its largest possible region, users should call UpdateLargestPossibleRegion() instead. Reimplemented from itk::ProcessObject.

virtual void itk::ProcessObject::UpdateLargestPossibleRegion (   )  [virtual, inherited]

Like Update(), but sets the output requested region to the largest possible region for the output. This is the method users should call if they want the entire dataset to be processed. If a user wants to update the same output region as a previous call to Update() or a previous call to UpdateLargestPossibleRegion(), then they should call the method Update().

virtual void itk::ProcessObject::UpdateOutputData (  DataObject *  output  )  [virtual, inherited]

Actually generate new output Reimplemented in itk::StreamingImageFilter< TInputImage, TOutputImage >.

virtual void itk::ProcessObject::UpdateOutputInformation (   )  [virtual, inherited]

Update the information decribing the output data. This method transverses up the pipeline gathering modified time information. On the way back down the pipeline, this method calls GenerateOutputInformation() to set any necessary information about the output data objects. For instance, a filter that shrinks an image will need to provide an implementation for GenerateOutputInformation() that changes the spacing of the pixels. Such filters should call their superclass' implementation of GenerateOutputInformation prior to changing the information values they need (i.e. GenerateOutputInformation() should call Superclass::GenerateOutputInformation() prior to changing the information. Reimplemented in itk::watershed::Segmenter< TInputImage >, and itk::VTKImageImport< TOutputImage >.

void itk::ProcessObject::UpdateProgress (  float  amount  )  [inherited]

Update the progress of the process object. Sets the Progress ivar to amount and invokes any observers for the ProgressEvent. The parameter amount should be in [0,1] and is the cumulative (not incremental) progress.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::UseLandmarks (  bool  b  )  [inline]

This determines if the landmark file will be read Definition at line 256 of file itkFEMRegistrationFilter.h.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::WarpImage (  const MovingImageType *  R  )

Applies the warp to the input image.

template<class TMovingImage, class TFixedImage> int itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::WriteDisplacementField (  unsigned int  index  )

Writes the displacement field to a file.

template<class TMovingImage, class TFixedImage> int itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::WriteDisplacementFieldMultiComponent (   )

Writes the displacement field to a file as a single volume with multiple components.

template<class TMovingImage, class TFixedImage> void itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::WriteWarpedImage (  const char *  fn  )

Call this to write out images - a counter is attached to the file name so we can output a numbered sequence tracking the deformation.

---

Member Data Documentation

Allow people to add remove invoke observers (callbacks) to any ITK * object. This is an implementation of the subject/observer design * pattern. An observer is added by specifying an event to respond to * and an itk unsigned lon itk::Object::AddObserver)(const EventObject &event, Command *) const [inherited]

Push Pop the input of this process object These methods allow a* filter to model its input vector as a queue or stack These* routines may not be appropriate for all especially* filters with different types of inputs These routines follow* the semantics of STL* * The routines are useful for applications that need to process* rolling sets of images For if an application has* images and they need to run a filter on then* run the filter on then run the filter on the application can accomplish this by popping* an input off the front of the input list and push a new image* onto the back of input list itk::ImageToImageFilter< TMovingImage , TFixedImage >::Again [inherited]

Definition at line 103 of file itkImageToImageFilter.h.

This is a global flag that controls whether any itk::Object::debug [inherited]

Definition at line 94 of file itkObject.h.

template<class TMovingImage, class TFixedImage> The FEM filter can generate its own mesh for or itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::dimensions

Definition at line 282 of file itkFEMRegistrationFilter.h.

* endcode* In the above itk::ImageSource< TFixedImage >::example [inherited]

Definition at line 100 of file itkImageSource.h.

template<class TMovingImage, class TFixedImage> Re size the vector field (smaller to larger). */ typedef typename FieldType FieldPointe itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::ExpandVectorField)(ExpandFactorsType *expandFactors, FieldType *f) [protected]

Push Pop the input of this process object These methods allow a* filter to model its input vector as a queue or stack These* routines may not be appropriate for all especially* filters with different types of inputs These routines follow* the semantics of STL* * The routines are useful for applications that need to process* rolling sets of images For if an application has* images and they need to run a filter on then* run the filter on then run the filter on the application can accomplish this by popping* an input off the front of the input list and push a new image* onto the back of input list this only makes sense for* filters that single type of input* * Other uses are also possible For a single input itk::ImageToImageFilter< TMovingImage , TFixedImage >::filter [inherited]

Definition at line 103 of file itkImageToImageFilter.h.

Push Pop the input of this process object These methods allow a* filter to model its input vector as a queue or stack These* routines may not be appropriate for all itk::ImageToImageFilter< TMovingImage , TFixedImage >::filters [inherited]

Reimplemented from itk::ProcessObject. Definition at line 103 of file itkImageToImageFilter.h.

* * these methods end of hiding the versions from the superclass* ProcessObject whose arguments are DataObjects itk::ImageToImageFilter< TMovingImage , TFixedImage >::Here [protected, inherited]

Definition at line 246 of file itkImageToImageFilter.h.

* itk::ImageSource< TFixedImage >::image [inherited]

Definition at line 98 of file itkImageSource.h.

* endcode* * In this a someFilter and a anotherFilter are said* to constitute a b pipeline* * code* itk::ImageSource< TFixedImage >::image [inherited]

Definition at line 92 of file itkImageSource.h.

Push Pop the input of this process object These methods allow a* filter to model its input vector as a queue or stack These* routines may not be appropriate for all especially* filters with different types of inputs These routines follow* the semantics of STL* * The routines are useful for applications that need to process* rolling sets of images For if an application has* images and they need to run a filter on then* run the filter on then run the filter on* itk::ImageToImageFilter< TMovingImage , TFixedImage >::images [inherited]

Definition at line 103 of file itkImageToImageFilter.h.

Push Pop the input of this process object These methods allow a* filter to model its input vector as a queue or stack These* routines may not be appropriate for all especially* filters with different types of inputs These routines follow* the semantics of STL* * The routines are useful for applications that need to process* rolling sets of images For if an application has* images and they need to run a filter on then* run the filter on itk::ImageToImageFilter< TMovingImage , TFixedImage >::images [inherited]

Definition at line 103 of file itkImageToImageFilter.h.

Push Pop the input of this process object These methods allow a* filter to model its input vector as a queue or stack These* routines may not be appropriate for all especially* filters with different types of inputs These routines follow* the semantics of STL* * The routines are useful for applications that need to process* rolling sets of images For if an application has* images and they need to run a filter on itk::ImageToImageFilter< TMovingImage , TFixedImage >::images [inherited]

Definition at line 103 of file itkImageToImageFilter.h.

Push Pop the input of this process object These methods allow a* filter to model its input vector as a queue or stack These* routines may not be appropriate for all especially* filters with different types of inputs These routines follow* the semantics of STL* * The routines are useful for applications that need to process* rolling sets of images For itk::ImageToImageFilter< TMovingImage , TFixedImage >::instance [inherited]

Definition at line 103 of file itkImageToImageFilter.h.

TimeStamp itk::ProcessObject::m_OutputInformationMTime [protected, inherited]

Time when GenerateOutputInformation was last called. Definition at line 428 of file itkProcessObject.h.

int itk::LightObject::m_ReferenceCount [mutable, protected, inherited]

Number of uses of this object by other objects. Definition at line 119 of file itkLightObject.h.

SimpleFastMutexLock itk::LightObject::m_ReferenceCountLock [mutable, protected, inherited]

Mutex lock to protect modification to the reference count Definition at line 122 of file itkLightObject.h.

bool itk::ProcessObject::m_Updating [protected, inherited]

This flag indicates when the pipeline is executing. It prevents infinite recursion when pipelines have loops. Definition at line 425 of file itkProcessObject.h.

Get the output data of this process object The output of this* function is not valid until an appropriate either explicitly or implicitly Both the filter* itself and the data object have and both* methods update the data Here are three ways to use* a image is a pointer to some Image itk::ImageSource< TFixedImage >::object [inherited]

Definition at line 79 of file itkImageSource.h.

Methods invoked by virtual Print () to print information about the object * including superclasses. Typically not called by the user (use Print() * instead) but used in the hierarchical print process to combine the * output of several classes. */ virtual void PrintSelf(std voi itk::LightObject::PrintHeader)(std::ostream &os, Indent indent) const [protected, inherited]

* endcode* In the above the two lines of code can be in* either order* * Note that it may be more efficient to* use a pipeline than to call the data generated is for the requested* itk::ImageSource< TFixedImage >::Region [inherited]

Definition at line 110 of file itkImageSource.h.

template<class TMovingImage, class TFixedImage> The FEM filter can generate its own mesh for or if none is provided The mesh is generated for quadrilaterals in D and hexahedra in D This function sets the number of elements generated along each dimension at the resolution designated by which E g to generate pixels per element in each dimension in the st itk::fem::FEMRegistrationFilter< TMovingImage, TFixedImage >::resolution

Definition at line 282 of file itkFEMRegistrationFilter.h.

* endcode* * In this itk::ImageSource< TFixedImage >::situation [inherited]

Definition at line 88 of file itkImageSource.h.

---

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

• itkFEMRegistrationFilter.h

---