itk::simple::ImageRegistrationMethod Class Reference

An interface method to the modular ITKv4 registration framework. More...

#include <sitkImageRegistrationMethod.h>

Inheritance diagram for itk::simple::ImageRegistrationMethod:

Collaboration diagram for itk::simple::ImageRegistrationMethod:

Classes
struct	EvaluateMemberFunctionAddressor

Public Types
enum	EstimateLearningRateType {   Never,   Once,   EachIteration }
enum	MetricSamplingStrategyType {   NONE,   REGULAR,   RANDOM }
typedef ImageRegistrationMethod	Self
typedef ProcessObject	Superclass
Public Types inherited from itk::simple::ProcessObject
typedef ProcessObject	Self

Public Member Functions
Transform	Execute (const Image &fixed, const Image &moving)
	Optimize the configured registration problem. More...
unsigned int	GetCurrentLevel () const
double	GetMetricValue () const
std::string	GetName () const
double	GetOptimizerConvergenceValue () const
unsigned int	GetOptimizerIteration () const
double	GetOptimizerLearningRate () const
std::vector< double >	GetOptimizerPosition () const
std::vector< double >	GetOptimizerScales () const
	Get the OptimizerScales. More...
std::string	GetOptimizerStopConditionDescription () const
	ImageRegistrationMethod ()
double	MetricEvaluate (const Image &fixed, const Image &moving)
	Get the value of the metric given the state of the method. More...
Self &	SetMetricAsANTSNeighborhoodCorrelation (unsigned int radius)
	Use normalized cross correlation using a small neighborhood for each voxel between two images, with speed optimizations for dense registration. More...
Self &	SetMetricAsCorrelation ()
	Use negative normalized cross correlation image metric. More...
Self &	SetMetricAsDemons (double intensityDifferenceThreshold=0.001)
	Use demons image metric. More...
Self &	SetMetricAsJointHistogramMutualInformation (unsigned int numberOfHistogramBins=20, double varianceForJointPDFSmoothing=1.5)
	Use mutual information between two images. More...
Self &	SetMetricAsMattesMutualInformation (unsigned int numberOfHistogramBins=50)
	Use the mutual information between two images to be registered using the method of Mattes et al. More...
Self &	SetMetricAsMeanSquares ()
	Use negative means squares image metric. More...
Self &	SetMetricFixedMask (const Image &binaryMask)
	Set an image mask in order to restrict the sampled points for the metric. More...
Self &	SetMetricMovingMask (const Image &binaryMask)
	Set an image mask in order to restrict the sampled points for the metric in the moving image space. More...
Self &	SetMetricSamplingStrategy (MetricSamplingStrategyType strategy)
	Set sampling strategy for sample generation. More...
Self &	SetOptimizerAsAmoeba (double simplexDelta, unsigned int numberOfIterations, double parametersConvergenceTolerance=1e-8, double functionConvergenceTolerance=1e-4, bool withRestarts=false)
	Set optimizer to Nelder-Mead downhill simplex algorithm. More...
Self &	SetOptimizerAsConjugateGradientLineSearch (double learningRate, unsigned int numberOfIterations, double convergenceMinimumValue=1e-6, unsigned int convergenceWindowSize=10, double lineSearchLowerLimit=0, double lineSearchUpperLimit=5.0, double lineSearchEpsilon=0.01, unsigned int lineSearchMaximumIterations=20, EstimateLearningRateType estimateLearningRate=Once, double maximumStepSizeInPhysicalUnits=0.0)
	Conjugate gradient descent optimizer with a golden section line search for nonlinear optimization. More...
Self &	SetOptimizerAsExhaustive (const std::vector< unsigned int > &numberOfSteps, double stepLength=1.0)
	Set the optimizer to sample the metric at regular steps. More...
Self &	SetOptimizerAsGradientDescent (double learningRate, unsigned int numberOfIterations, double convergenceMinimumValue=1e-6, unsigned int convergenceWindowSize=10, EstimateLearningRateType estimateLearningRate=Once, double maximumStepSizeInPhysicalUnits=0.0)
	Gradient descent optimizer. More...
Self &	SetOptimizerAsGradientDescentLineSearch (double learningRate, unsigned int numberOfIterations, double convergenceMinimumValue=1e-6, unsigned int convergenceWindowSize=10, double lineSearchLowerLimit=0, double lineSearchUpperLimit=5.0, double lineSearchEpsilon=0.01, unsigned int lineSearchMaximumIterations=20, EstimateLearningRateType estimateLearningRate=Once, double maximumStepSizeInPhysicalUnits=0.0)
	Gradient descent optimizer with a golden section line search. More...
Self &	SetOptimizerAsLBFGSB (double gradientConvergenceTolerance=1e-5, unsigned int numberOfIterations=500, unsigned int maximumNumberOfCorrections=5, unsigned int maximumNumberOfFunctionEvaluations=2000, double costFunctionConvergenceFactor=1e+7, double lowerBound=std::numeric_limits< double >::min(), double upperBound=std::numeric_limits< double >::max(), bool trace=false)
	Limited memory Broyden Fletcher Goldfarb Shannon minimization with simple bounds. More...
Self &	SetOptimizerAsOnePlusOneEvolutionary (unsigned int numberOfIterations=100, double epsilon=1.5e-4, double initialRadius=1.01, double growthFactor=-1.0, double shrinkFactor=-1.0, unsigned int seed=sitkWallClock)
	1+1 evolutionary optimizer strategy. More...
Self &	SetOptimizerAsPowell (unsigned int numberOfIterations=100, unsigned int maximumLineIterations=100, double stepLength=1, double stepTolerance=1e-6, double valueTolerance=1e-6)
	Powell optimization using Brent line search. More...
Self &	SetOptimizerAsRegularStepGradientDescent (double learningRate, double minStep, unsigned int numberOfIterations, double relaxationFactor=0.5, double gradientMagnitudeTolerance=1e-4, EstimateLearningRateType estimateLearningRate=Never, double maximumStepSizeInPhysicalUnits=0.0)
	Regular Step Gradient descent optimizer. More...
Self &	SetOptimizerScales (const std::vector< double > &scales)
	Manually set per parameter weighting for the transform parameters. More...
Self &	SetOptimizerScalesFromIndexShift (unsigned int centralRegionRadius=5, double smallParameterVariation=0.01)
	Estimate scales from maximum voxel shift in index space cause by parameter change. More...
Self &	SetOptimizerScalesFromJacobian (unsigned int centralRegionRadius=5)
	Estimate scales from Jacobian norms. More...
Self &	SetOptimizerScalesFromPhysicalShift (unsigned int centralRegionRadius=5, double smallParameterVariation=0.01)
	Estimating scales of transform parameters a step sizes, from the maximum voxel shift in physical space caused by a parameter change. More...
Self &	SetShrinkFactorsPerLevel (const std::vector< unsigned int > &shrinkFactors)
	Set the shrink factors for each level where each level has the same shrink factor for each dimension. More...
Self &	SetSmoothingSigmasPerLevel (const std::vector< double > &smoothingSigmas)
	Set the sigmas of Gaussian used for smoothing at each level. More...
std::string	ToString () const
	Print the information about the object to a string. More...
virtual	~ImageRegistrationMethod ()
InterpolatorEnum	GetInterpolator ()
	Set and get the interpolator to use. More...
Self &	SetInterpolator (InterpolatorEnum Interpolator)
	Set and get the interpolator to use. More...
Self &	SetInitialTransform (const Transform &transform)
	Set the initial transform and parameters to optimize. More...
Self &	SetInitialTransform (Transform &transform, bool inPlace=true)
	Set the initial transform and parameters to optimize. More...
Transform	GetInitialTransform ()
	Set the initial transform and parameters to optimize. More...
bool	GetInitialTransformInPlace () const
	Set the initial transform and parameters to optimize. More...
Self &	SetMovingInitialTransform (const Transform &transform)
	Set a fixed transform component towards moving domain. More...
Transform	GetMovingInitialTransform () const
	Set a fixed transform component towards moving domain. More...
Self &	SetFixedInitialTransform (const Transform &transform)
	Set transform mapping to the fixed domain. More...
Transform	GetFixedInitialTransform () const
	Set transform mapping to the fixed domain. More...
Self &	SetVirtualDomain (const std::vector< uint32_t > &virtualSize, const std::vector< double > &virtualOrigin, const std::vector< double > &virtualSpacing, const std::vector< double > &virtualDirection)
	Set the virtual domain used for sampling. More...
Self &	SetVirtualDomainFromImage (const Image &virtualImage)
	Set the virtual domain used for sampling. More...
Self &	SetOptimizerWeights (const std::vector< double > &weights)
	A per parameter weighting array for the optimizer. More...
std::vector< double >	GetOptimizerWeights () const
	A per parameter weighting array for the optimizer. More...
Self &	SetMetricSamplingPercentage (double percentage, unsigned int seed=sitkWallClock)
	Set percentage of pixels sampled for metric evaluation. More...
Self &	SetMetricSamplingPercentagePerLevel (const std::vector< double > &percentage, unsigned int seed=sitkWallClock)
	Set percentage of pixels sampled for metric evaluation. More...
Self &	SetMetricUseFixedImageGradientFilter (bool)
	Enable image gradient computation by a filter. More...
Self &	MetricUseFixedImageGradientFilterOn ()
	Enable image gradient computation by a filter. More...
Self &	MetricUseFixedImageGradientFilterOff ()
	Enable image gradient computation by a filter. More...
Self &	SetMetricUseMovingImageGradientFilter (bool)
	Enable image gradient computation by a filter. More...
Self &	MetricUseMovingImageGradientFilterOn ()
	Enable image gradient computation by a filter. More...
Self &	MetricUseMovingImageGradientFilterOff ()
	Enable image gradient computation by a filter. More...
Self &	SetSmoothingSigmasAreSpecifiedInPhysicalUnits (bool arg)
	Enable the smoothing sigmas for each level in physical units (default) or in terms of voxels. More...
Self &	SmoothingSigmasAreSpecifiedInPhysicalUnitsOn ()
	Enable the smoothing sigmas for each level in physical units (default) or in terms of voxels. More...
Self &	SmoothingSigmasAreSpecifiedInPhysicalUnitsOff ()
	Enable the smoothing sigmas for each level in physical units (default) or in terms of voxels. More...
Public Member Functions inherited from itk::simple::ProcessObject
virtual void	Abort ()
virtual int	AddCommand (itk::simple::EventEnum event, itk::simple::Command &cmd)
	Add a Command Object to observer the event. More...
virtual float	GetProgress () const
	An Active Measurement of the progress of execution. More...
virtual bool	HasCommand (itk::simple::EventEnum event) const
	Query of this object has any registered commands for event. More...
	ProcessObject ()
virtual void	RemoveAllCommands ()
	Remove all registered commands. More...
virtual	~ProcessObject ()
virtual void	DebugOn ()
virtual void	DebugOff ()
virtual bool	GetDebug () const
virtual void	SetDebug (bool debugFlag)
virtual void	SetNumberOfThreads (unsigned int n)
virtual unsigned int	GetNumberOfThreads () const

Protected Member Functions
virtual unsigned long	AddITKObserver (const itk::EventObject &, itk::Command *)
template<class TImageType >
itk::ImageToImageMetricv4< TImageType, TImageType, TImageType, double, itk::DefaultImageToImageMetricTraitsv4< TImageType, TImageType, TImageType, double > > *	CreateMetric ()
itk::ObjectToObjectOptimizerBaseTemplate< double > *	CreateOptimizer (unsigned int numberOfTransformParameters)
template<typename TMetric >
itk::RegistrationParameterScalesEstimator< TMetric > *	CreateScalesEstimator ()
template<unsigned int VDimension>
itk::SpatialObject< VDimension > *	CreateSpatialObjectMask (const Image &mask)
template<typename TTransformAdaptorPointer , typename TRegistrationMethod >
std::vector< TTransformAdaptorPointer >	CreateTransformParametersAdaptor (TRegistrationMethod *method)
template<class TImage >
double	EvaluateInternal (const Image &fixed, const Image &moving)
template<class TImage >
Transform	ExecuteInternal (const Image &fixed, const Image &moving)
virtual void	OnActiveProcessDelete () throw ()
virtual void	PreUpdate (itk::ProcessObject *p)
virtual void	RemoveITKObserver (EventCommand &e)
template<class TImageType >
void	SetupMetric (itk::ImageToImageMetricv4< TImageType, TImageType, TImageType, double, itk::DefaultImageToImageMetricTraitsv4< TImageType, TImageType, TImageType, double > > *, const TImageType *, const TImageType *)
Protected Member Functions inherited from itk::simple::ProcessObject
virtual itk::ProcessObject *	GetActiveProcess ()
virtual void	onCommandDelete (const itk::simple::Command *cmd) throw ()
Protected Member Functions inherited from itk::simple::NonCopyable
	NonCopyable ()

Private Types
typedef double(ImageRegistrationMethod::*	EvaluateMemberFunctionType) (const Image &fixed, const Image &moving)
typedef Transform(ImageRegistrationMethod::*	MemberFunctionType) (const Image &fixed, const Image &moving)
enum	MetricType {   ANTSNeighborhoodCorrelation,   Correlation,   Demons,   JointHistogramMutualInformation,   MeanSquares,   MattesMutualInformation }
enum	OptimizerScalesType {   Manual,   Jacobian,   IndexShift,   PhysicalShift }
enum	OptimizerType {   ConjugateGradientLineSearch,   RegularStepGradientDescent,   GradientDescent,   GradientDescentLineSearch,   LBFGSB,   Exhaustive,   Amoeba,   Powell,   OnePlusOneEvolutionary }

Private Attributes
itk::ObjectToObjectOptimizerBaseTemplate< double > *	m_ActiveOptimizer
nsstd::auto_ptr< detail::MemberFunctionFactory< EvaluateMemberFunctionType > >	m_EvaluateMemberFactory
Transform	m_FixedInitialTransform
Transform	m_InitialTransform
bool	m_InitialTransformInPlace
InterpolatorEnum	m_Interpolator
unsigned int	m_Iteration
nsstd::auto_ptr< detail::MemberFunctionFactory< MemberFunctionType > >	m_MemberFactory
Image	m_MetricFixedMaskImage
double	m_MetricIntensityDifferenceThreshold
Image	m_MetricMovingMaskImage
unsigned int	m_MetricNumberOfHistogramBins
unsigned int	m_MetricRadius
std::vector< double >	m_MetricSamplingPercentage
unsigned int	m_MetricSamplingSeed
MetricSamplingStrategyType	m_MetricSamplingStrategy
MetricType	m_MetricType
bool	m_MetricUseFixedImageGradientFilter
bool	m_MetricUseMovingImageGradientFilter
double	m_MetricValue
double	m_MetricVarianceForJointPDFSmoothing
Transform	m_MovingInitialTransform
double	m_OptimizerConvergenceMinimumValue
unsigned int	m_OptimizerConvergenceWindowSize
double	m_OptimizerCostFunctionConvergenceFactor
double	m_OptimizerEpsilon
EstimateLearningRateType	m_OptimizerEstimateLearningRate
double	m_OptimizerFunctionConvergenceTolerance
double	m_OptimizerGradientConvergenceTolerance
double	m_OptimizerGradientMagnitudeTolerance
double	m_OptimizerGrowthFactor
double	m_OptimizerInitialRadius
double	m_OptimizerLearningRate
double	m_OptimizerLineSearchEpsilon
double	m_OptimizerLineSearchLowerLimit
unsigned int	m_OptimizerLineSearchMaximumIterations
double	m_OptimizerLineSearchUpperLimit
double	m_OptimizerLowerBound
unsigned int	m_OptimizerMaximumLineIterations
unsigned int	m_OptimizerMaximumNumberOfCorrections
unsigned int	m_OptimizerMaximumNumberOfFunctionEvaluations
double	m_OptimizerMaximumStepSizeInPhysicalUnits
double	m_OptimizerMinimumStepLength
unsigned int	m_OptimizerNumberOfIterations
std::vector< unsigned int >	m_OptimizerNumberOfSteps
double	m_OptimizerParametersConvergenceTolerance
double	m_OptimizerRelaxationFactor
std::vector< double >	m_OptimizerScales
unsigned int	m_OptimizerScalesCentralRegionRadius
double	m_OptimizerScalesSmallParameterVariation
OptimizerScalesType	m_OptimizerScalesType
unsigned int	m_OptimizerSeed
double	m_OptimizerShrinkFactor
double	m_OptimizerSimplexDelta
double	m_OptimizerStepLength
double	m_OptimizerStepTolerance
bool	m_OptimizerTrace
OptimizerType	m_OptimizerType
double	m_OptimizerUpperBound
double	m_OptimizerValueTolerance
std::vector< double >	m_OptimizerWeights
bool	m_OptimizerWithRestarts
nsstd::function< unsigned int()>	m_pfGetCurrentLevel
nsstd::function< double()>	m_pfGetMetricValue
nsstd::function< double()>	m_pfGetOptimizerConvergenceValue
nsstd::function< unsigned int()>	m_pfGetOptimizerIteration
nsstd::function< double()>	m_pfGetOptimizerLearningRate
nsstd::function< std::vector< double >)>	m_pfGetOptimizerPosition
nsstd::function< std::vector< double >)>	m_pfGetOptimizerScales
nsstd::function< std::string()>	m_pfGetOptimizerStopConditionDescription
nsstd::function< void(itk::TransformBase *outTransform)>	m_pfUpdateWithBestValue
std::vector< unsigned int >	m_ShrinkFactorsPerLevel
bool	m_SmoothingSigmasAreSpecifiedInPhysicalUnits
std::vector< double >	m_SmoothingSigmasPerLevel
std::string	m_StopConditionDescription
std::vector< double >	m_VirtualDomainDirection
std::vector< double >	m_VirtualDomainOrigin
std::vector< uint32_t >	m_VirtualDomainSize
std::vector< double >	m_VirtualDomainSpacing

Friends
struct	detail::MemberFunctionAddressor< MemberFunctionType >

Additional Inherited Members
Static Public Member Functions inherited from itk::simple::ProcessObject
static bool	GetGlobalDefaultDebug ()
static void	GlobalDefaultDebugOff ()
static void	GlobalDefaultDebugOn ()
static void	SetGlobalDefaultDebug (bool debugFlag)
static void	GlobalWarningDisplayOn ()
static void	GlobalWarningDisplayOff ()
static void	SetGlobalWarningDisplay (bool flag)
static bool	GetGlobalWarningDisplay ()
static void	SetGlobalDefaultNumberOfThreads (unsigned int n)
static unsigned int	GetGlobalDefaultNumberOfThreads ()
static double	GetGlobalDefaultCoordinateTolerance ()
	Access the global tolerance to determine congruent spaces. More...
static void	SetGlobalDefaultCoordinateTolerance (double)
	Access the global tolerance to determine congruent spaces. More...
static double	GetGlobalDefaultDirectionTolerance ()
	Access the global tolerance to determine congruent spaces. More...
static void	SetGlobalDefaultDirectionTolerance (double)
	Access the global tolerance to determine congruent spaces. More...
Static Protected Member Functions inherited from itk::simple::ProcessObject
template<class TImageType >
static TImageType::ConstPointer	CastImageToITK (const Image &img)
template<class TImageType >
static Image	CastITKToImage (TImageType *img)
template<class TPixelType , unsigned int VImageDimension, unsigned int VLength, template< typename, unsigned int > class TVector>
static Image	CastITKToImage (itk::Image< TVector< TPixelType, VLength >, VImageDimension > *img)
static const itk::EventObject &	GetITKEventObject (EventEnum e)
template<typename T >
static std::ostream &	ToStringHelper (std::ostream &os, const T &v)
static std::ostream &	ToStringHelper (std::ostream &os, const char &v)
static std::ostream &	ToStringHelper (std::ostream &os, const signed char &v)
static std::ostream &	ToStringHelper (std::ostream &os, const unsigned char &v)

Detailed Description

An interface method to the modular ITKv4 registration framework.

This interface method class encapsulates typical registration usage by incorporating all the necessary elements for performing a simple image registration between two images. This method also allows for multistage registration whereby each stage is characterized by possibly different transforms and different image metrics. For example, many users will want to perform a linear registration followed by deformable registration where both stages are performed in multiple levels. Each level can be characterized by:

• the resolution of the virtual domain image (see below)
• smoothing of the fixed and moving images

Multiple stages are handled by linking multiple instantiations of this class where the output transform is added to the optional composite transform input.

See also

itk::ImageRegistrationMethodv4

itk::ImageToImageMetricv4

itk::ObjectToObjectOptimizerBaseTemplate

Examples:

ImageRegistrationMethod1/ImageRegistrationMethod1.cxx, ImageRegistrationMethod2/ImageRegistrationMethod2.cxx, ImageRegistrationMethodBSpline1/ImageRegistrationMethodBSpline1.cxx, and ImageRegistrationMethodDisplacement1/ImageRegistrationMethodDisplacement1.cxx.

Definition at line 88 of file sitkImageRegistrationMethod.h.

Member Typedef Documentation

typedef double(ImageRegistrationMethod::* itk::simple::ImageRegistrationMethod::EvaluateMemberFunctionType) (const Image &fixed, const Image &moving)

private

Definition at line 627 of file sitkImageRegistrationMethod.h.

typedef Transform(ImageRegistrationMethod::* itk::simple::ImageRegistrationMethod::MemberFunctionType) (const Image &fixed, const Image &moving)

private

Definition at line 626 of file sitkImageRegistrationMethod.h.

typedef ImageRegistrationMethod itk::simple::ImageRegistrationMethod::Self

Definition at line 93 of file sitkImageRegistrationMethod.h.

typedef ProcessObject itk::simple::ImageRegistrationMethod::Superclass

Definition at line 94 of file sitkImageRegistrationMethod.h.

Member Enumeration Documentation

enum itk::simple::ImageRegistrationMethod::EstimateLearningRateType

Enumerator
Never	Never run estimation, use provided value.
Once	Estimate learning once each level, ignore provided values.
EachIteration	Estimate learning rate at each iteration.

Examples:

ImageRegistrationMethodDisplacement1/ImageRegistrationMethodDisplacement1.cxx.

Definition at line 234 of file sitkImageRegistrationMethod.h.

enum itk::simple::ImageRegistrationMethod::MetricSamplingStrategyType

Enumerator
NONE
REGULAR
RANDOM

Definition at line 443 of file sitkImageRegistrationMethod.h.

enum itk::simple::ImageRegistrationMethod::MetricType

private

Enumerator
ANTSNeighborhoodCorrelation
Correlation
Demons
JointHistogramMutualInformation
MeanSquares
MattesMutualInformation

Definition at line 704 of file sitkImageRegistrationMethod.h.

enum itk::simple::ImageRegistrationMethod::OptimizerScalesType

private

Enumerator
Manual
Jacobian
IndexShift
PhysicalShift

Definition at line 692 of file sitkImageRegistrationMethod.h.

enum itk::simple::ImageRegistrationMethod::OptimizerType

private

Enumerator
ConjugateGradientLineSearch
RegularStepGradientDescent
GradientDescent
GradientDescentLineSearch
LBFGSB
Exhaustive
Amoeba
Powell
OnePlusOneEvolutionary

Definition at line 644 of file sitkImageRegistrationMethod.h.

Constructor & Destructor Documentation

itk::simple::ImageRegistrationMethod::ImageRegistrationMethod

(

)

virtual itk::simple::ImageRegistrationMethod::~ImageRegistrationMethod ( )

virtual

Member Function Documentation

virtual unsigned long itk::simple::ImageRegistrationMethod::AddITKObserver ( const itk::EventObject &  , itk::Command *    )

protectedvirtual

Reimplemented from itk::simple::ProcessObject.

template<class TImageType >

itk::ImageToImageMetricv4<TImageType, TImageType, TImageType, double, itk::DefaultImageToImageMetricTraitsv4< TImageType, TImageType, TImageType, double > >* itk::simple::ImageRegistrationMethod::CreateMetric ( )

protected

itk::ObjectToObjectOptimizerBaseTemplate<double>* itk::simple::ImageRegistrationMethod::CreateOptimizer ( unsigned int  numberOfTransformParameters )

protected

template<typename TMetric >

itk::RegistrationParameterScalesEstimator< TMetric >* itk::simple::ImageRegistrationMethod::CreateScalesEstimator ( )

protected

template<unsigned int VDimension>

itk::SpatialObject<VDimension>* itk::simple::ImageRegistrationMethod::CreateSpatialObjectMask ( const Image &  mask )

protected

template<typename TTransformAdaptorPointer , typename TRegistrationMethod >

std::vector< TTransformAdaptorPointer > itk::simple::ImageRegistrationMethod::CreateTransformParametersAdaptor ( TRegistrationMethod *  method )

protected

template<class TImage >

double itk::simple::ImageRegistrationMethod::EvaluateInternal ( const Image &  fixed, const Image &  moving  )

protected

Transform itk::simple::ImageRegistrationMethod::Execute	(	const Image &	fixed,
		const Image &	moving
	)

Optimize the configured registration problem.

Examples:

ImageRegistrationMethod1/ImageRegistrationMethod1.cxx, ImageRegistrationMethod2/ImageRegistrationMethod2.cxx, ImageRegistrationMethodBSpline1/ImageRegistrationMethodBSpline1.cxx, and ImageRegistrationMethodDisplacement1/ImageRegistrationMethodDisplacement1.cxx.

template<class TImage >

Transform itk::simple::ImageRegistrationMethod::ExecuteInternal ( const Image &  fixed, const Image &  moving  )

protected

unsigned int itk::simple::ImageRegistrationMethod::GetCurrentLevel

(

)

const

Transform itk::simple::ImageRegistrationMethod::GetFixedInitialTransform ( ) const

inline

Set transform mapping to the fixed domain.

This transform is used to map from the virtual domain to the fixed image domain.

By default this transform is an identity, and not used.

See also

itk::ImageRegistrationMethodv4::SetFixedInitialTransform

Definition at line 177 of file sitkImageRegistrationMethod.h.

Transform itk::simple::ImageRegistrationMethod::GetInitialTransform ( )

inline

Set the initial transform and parameters to optimize.

This transform is applied before the MovingInitialTransform, to map from the virtual image domain to the moving image domain.

If the inPlace flag is explicitly false, then the ITK registration will internally make a copy, and the transform will not be accessible during registration. Otherwise, the accessible InitialTransform value will be the same object used during registration, and will have a modified value upon completion.

See also

itk::ImageRegistrationMethodv4::SetInitialTransform

Definition at line 140 of file sitkImageRegistrationMethod.h.

bool itk::simple::ImageRegistrationMethod::GetInitialTransformInPlace ( ) const

inline

Set the initial transform and parameters to optimize.

This transform is applied before the MovingInitialTransform, to map from the virtual image domain to the moving image domain.

If the inPlace flag is explicitly false, then the ITK registration will internally make a copy, and the transform will not be accessible during registration. Otherwise, the accessible InitialTransform value will be the same object used during registration, and will have a modified value upon completion.

See also

itk::ImageRegistrationMethodv4::SetInitialTransform

Definition at line 142 of file sitkImageRegistrationMethod.h.

InterpolatorEnum itk::simple::ImageRegistrationMethod::GetInterpolator ( )

inline

Set and get the interpolator to use.

Definition at line 113 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::GetMetricValue

(

)

const

Examples:

ImageRegistrationMethod1/ImageRegistrationMethod1.cxx, ImageRegistrationMethod2/ImageRegistrationMethod2.cxx, ImageRegistrationMethodBSpline1/ImageRegistrationMethodBSpline1.cxx, and ImageRegistrationMethodDisplacement1/ImageRegistrationMethodDisplacement1.cxx.

Transform itk::simple::ImageRegistrationMethod::GetMovingInitialTransform ( ) const

inline

Set a fixed transform component towards moving domain.

The InitialTransform is added to this transform to form the composite transform which maps from the virtual domain to the moving image's domain. The parameters of this transform are not optimized. This is an advanced option used when the output transformed with be composed into a composite transform.

By default this transform is an identity, and not used.

See also

itk::ImageRegistrationMethodv4::SetMovingInitialTransform

Definition at line 161 of file sitkImageRegistrationMethod.h.

std::string itk::simple::ImageRegistrationMethod::GetName ( ) const

inlinevirtual

return user readable name for the filter

Implements itk::simple::ProcessObject.

Definition at line 99 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::GetOptimizerConvergenceValue

(

)

const

unsigned int itk::simple::ImageRegistrationMethod::GetOptimizerIteration

(

)

const

Active measurements which can be obtained during call backs.

This is a measurement. Its value is updated in the Execute methods, so the value will only be valid after an execution.

Examples:

ImageRegistrationMethod1/ImageRegistrationMethod1.cxx, ImageRegistrationMethod2/ImageRegistrationMethod2.cxx, ImageRegistrationMethodBSpline1/ImageRegistrationMethodBSpline1.cxx, and ImageRegistrationMethodDisplacement1/ImageRegistrationMethodDisplacement1.cxx.

double itk::simple::ImageRegistrationMethod::GetOptimizerLearningRate

(

)

const

std::vector<double> itk::simple::ImageRegistrationMethod::GetOptimizerPosition

(

)

const

std::vector<double> itk::simple::ImageRegistrationMethod::GetOptimizerScales

(

)

const

Get the OptimizerScales.

If the scales are explicitly set then this method returns those values. If an estimator is used then this is an active measurement returning the scales estimated by the estimator and is only available during execution.

std::string itk::simple::ImageRegistrationMethod::GetOptimizerStopConditionDescription

(

)

const

Measurement updated at the end of execution.

Examples:

ImageRegistrationMethod1/ImageRegistrationMethod1.cxx, ImageRegistrationMethod2/ImageRegistrationMethod2.cxx, ImageRegistrationMethodBSpline1/ImageRegistrationMethodBSpline1.cxx, and ImageRegistrationMethodDisplacement1/ImageRegistrationMethodDisplacement1.cxx.

std::vector<double> itk::simple::ImageRegistrationMethod::GetOptimizerWeights

(

)

const

A per parameter weighting array for the optimizer.

Allows setting of a per-local-parameter weighting array. If unset, the weights are treated as identity. Weights are multiplied by the gradient at the same time scaling is applied. Weights are similar to the scales but not estimated, and may be used, for example, to easily mask out a particular parameter during optimization to hold it constant. Or they may be used to apply another kind of prior knowledge.

double itk::simple::ImageRegistrationMethod::MetricEvaluate	(	const Image &	fixed,
		const Image &	moving
	)

Get the value of the metric given the state of the method.

Passing a fixed and moving image, this method constructs and configures a metric object to obtain the value. This will take into consideration the current transforms, metric, interpolator, and image masks. It does not take into consideration the sampling strategy, smoothing sigmas, or the shrink factors.

Self& itk::simple::ImageRegistrationMethod::MetricUseFixedImageGradientFilterOff ( )

inline

Enable image gradient computation by a filter.

By default the image gradient is computed by itk::GradientRecursiveGaussianImageFiter. If disabled then a central difference function with be computed as needed.

See also

itk::ImageToImageMetricv4::SetUseFixedImageGradientFilter

Examples:

ImageRegistrationMethodDisplacement1/ImageRegistrationMethodDisplacement1.cxx.

Definition at line 466 of file sitkImageRegistrationMethod.h.

Self& itk::simple::ImageRegistrationMethod::MetricUseFixedImageGradientFilterOn ( )

inline

Enable image gradient computation by a filter.

By default the image gradient is computed by itk::GradientRecursiveGaussianImageFiter. If disabled then a central difference function with be computed as needed.

See also

itk::ImageToImageMetricv4::SetUseFixedImageGradientFilter

Definition at line 465 of file sitkImageRegistrationMethod.h.

Self& itk::simple::ImageRegistrationMethod::MetricUseMovingImageGradientFilterOff ( )

inline

Enable image gradient computation by a filter.

By default the image gradient is computed by itk::GradientRecursiveGaussianImageFiter. If disabled then a central difference function with be computed as needed.

See also

itk::ImageToImageMetricv4::SetUseMovingImageGradientFilter

Definition at line 481 of file sitkImageRegistrationMethod.h.

Self& itk::simple::ImageRegistrationMethod::MetricUseMovingImageGradientFilterOn ( )

inline

Enable image gradient computation by a filter.

By default the image gradient is computed by itk::GradientRecursiveGaussianImageFiter. If disabled then a central difference function with be computed as needed.

See also

itk::ImageToImageMetricv4::SetUseMovingImageGradientFilter

Definition at line 480 of file sitkImageRegistrationMethod.h.

virtual void itk::simple::ImageRegistrationMethod::OnActiveProcessDelete ( ) throw ( )

protectedvirtual

Reimplemented from itk::simple::ProcessObject.

virtual void itk::simple::ImageRegistrationMethod::PreUpdate ( itk::ProcessObject *  p )

protectedvirtual

Reimplemented from itk::simple::ProcessObject.

virtual void itk::simple::ImageRegistrationMethod::RemoveITKObserver ( EventCommand &  e )

protectedvirtual

Reimplemented from itk::simple::ProcessObject.

Self& itk::simple::ImageRegistrationMethod::SetFixedInitialTransform ( const Transform &  transform )

inline

Set transform mapping to the fixed domain.

This transform is used to map from the virtual domain to the fixed image domain.

By default this transform is an identity, and not used.

See also

itk::ImageRegistrationMethodv4::SetFixedInitialTransform

Definition at line 175 of file sitkImageRegistrationMethod.h.

Self& itk::simple::ImageRegistrationMethod::SetInitialTransform

(

const Transform &

transform

)

Set the initial transform and parameters to optimize.

This transform is applied before the MovingInitialTransform, to map from the virtual image domain to the moving image domain.

If the inPlace flag is explicitly false, then the ITK registration will internally make a copy, and the transform will not be accessible during registration. Otherwise, the accessible InitialTransform value will be the same object used during registration, and will have a modified value upon completion.

See also

itk::ImageRegistrationMethodv4::SetInitialTransform

Examples:

ImageRegistrationMethod1/ImageRegistrationMethod1.cxx, ImageRegistrationMethod2/ImageRegistrationMethod2.cxx, ImageRegistrationMethodBSpline1/ImageRegistrationMethodBSpline1.cxx, and ImageRegistrationMethodDisplacement1/ImageRegistrationMethodDisplacement1.cxx.

Self& itk::simple::ImageRegistrationMethod::SetInitialTransform	(	Transform &	transform,
		bool	inPlace = true
	)

Set the initial transform and parameters to optimize.

This transform is applied before the MovingInitialTransform, to map from the virtual image domain to the moving image domain.

If the inPlace flag is explicitly false, then the ITK registration will internally make a copy, and the transform will not be accessible during registration. Otherwise, the accessible InitialTransform value will be the same object used during registration, and will have a modified value upon completion.

See also

itk::ImageRegistrationMethodv4::SetInitialTransform

Self& itk::simple::ImageRegistrationMethod::SetInterpolator ( InterpolatorEnum  Interpolator )

inline

Set and get the interpolator to use.

Examples:

ImageRegistrationMethod1/ImageRegistrationMethod1.cxx, ImageRegistrationMethod2/ImageRegistrationMethod2.cxx, ImageRegistrationMethodBSpline1/ImageRegistrationMethodBSpline1.cxx, and ImageRegistrationMethodDisplacement1/ImageRegistrationMethodDisplacement1.cxx.

Definition at line 115 of file sitkImageRegistrationMethod.h.

Self& itk::simple::ImageRegistrationMethod::SetMetricAsANTSNeighborhoodCorrelation

(

unsigned int

radius

)

Use normalized cross correlation using a small neighborhood for each voxel between two images, with speed optimizations for dense registration.

See also

itk::ANTSNeighborhoodCorrelationImageToImageMetricv4

Examples:

ImageRegistrationMethodDisplacement1/ImageRegistrationMethodDisplacement1.cxx.

Self& itk::simple::ImageRegistrationMethod::SetMetricAsCorrelation

(

)

Use negative normalized cross correlation image metric.

See also

itk::CorrelationImageToImageMetricv4

Examples:

ImageRegistrationMethodBSpline1/ImageRegistrationMethodBSpline1.cxx.

Self& itk::simple::ImageRegistrationMethod::SetMetricAsDemons

(

double

intensityDifferenceThreshold = 0.001

)

Use demons image metric.

See also

itk::DemonsImageToImageMetricv4

Self& itk::simple::ImageRegistrationMethod::SetMetricAsJointHistogramMutualInformation	(	unsigned int	numberOfHistogramBins = 20,
		double	varianceForJointPDFSmoothing = 1.5
	)

Use mutual information between two images.

See also

itk::JointHistogramMutualInformationImageToImageMetricv4

Examples:

ImageRegistrationMethod2/ImageRegistrationMethod2.cxx, and ImageRegistrationMethodDisplacement1/ImageRegistrationMethodDisplacement1.cxx.

Self& itk::simple::ImageRegistrationMethod::SetMetricAsMattesMutualInformation

(

unsigned int

numberOfHistogramBins = 50

)

Use the mutual information between two images to be registered using the method of Mattes et al.

See also

itk::MattesMutualInformationImageToImageMetricv4

Self& itk::simple::ImageRegistrationMethod::SetMetricAsMeanSquares

(

)

Use negative means squares image metric.

See also

itk::MeanSquaresImageToImageMetricv4

Examples:

ImageRegistrationMethod1/ImageRegistrationMethod1.cxx.

Self& itk::simple::ImageRegistrationMethod::SetMetricFixedMask

(

const Image &

binaryMask

)

Set an image mask in order to restrict the sampled points for the metric.

The image is expected to be in the same physical space as the FixedImage, and if the pixel type is not UInt8 than the image will base cast.

See also

itk::ImageToImageMetricv4::SetFixedImageMask

Self& itk::simple::ImageRegistrationMethod::SetMetricMovingMask

(

const Image &

binaryMask

)

Set an image mask in order to restrict the sampled points for the metric in the moving image space.

The image is expected to be in the same physical space as the MovingImage, and if the pixel type is not UInt8 than the image will base cast.

See also

itk::ImageToImageMetricv4::SetMovingImageMask

Self& itk::simple::ImageRegistrationMethod::SetMetricSamplingPercentage	(	double	percentage,
		unsigned int	seed = sitkWallClock
	)

Set percentage of pixels sampled for metric evaluation.

The seed parameter is used to seed the pseudo-random number generator used in generating the sampling set of points. If the seed parameter is 0, then the wall clock is used, otherwise the fixed seed is used for reproducible behavior.

See also

itk::ImageRegistrationMethodv4::SetMetricSamplingPercentage

Self& itk::simple::ImageRegistrationMethod::SetMetricSamplingPercentagePerLevel	(	const std::vector< double > &	percentage,
		unsigned int	seed = sitkWallClock
	)

Set percentage of pixels sampled for metric evaluation.

The seed parameter is used to seed the pseudo-random number generator used in generating the sampling set of points. If the seed parameter is 0, then the wall clock is used, otherwise the fixed seed is used for reproducible behavior.

See also

itk::ImageRegistrationMethodv4::SetMetricSamplingPercentage

Self& itk::simple::ImageRegistrationMethod::SetMetricSamplingStrategy

(

MetricSamplingStrategyType

strategy

)

Set sampling strategy for sample generation.

See also

itk::ImageRegistrationMethodv4::SetMetricSamplingStrategy

Self& itk::simple::ImageRegistrationMethod::SetMetricUseFixedImageGradientFilter

(

bool

)

Enable image gradient computation by a filter.

By default the image gradient is computed by itk::GradientRecursiveGaussianImageFiter. If disabled then a central difference function with be computed as needed.

See also

itk::ImageToImageMetricv4::SetUseFixedImageGradientFilter

Self& itk::simple::ImageRegistrationMethod::SetMetricUseMovingImageGradientFilter

(

bool

)

Enable image gradient computation by a filter.

By default the image gradient is computed by itk::GradientRecursiveGaussianImageFiter. If disabled then a central difference function with be computed as needed.

See also

itk::ImageToImageMetricv4::SetUseMovingImageGradientFilter

Self& itk::simple::ImageRegistrationMethod::SetMovingInitialTransform ( const Transform &  transform )

inline

Set a fixed transform component towards moving domain.

The InitialTransform is added to this transform to form the composite transform which maps from the virtual domain to the moving image's domain. The parameters of this transform are not optimized. This is an advanced option used when the output transformed with be composed into a composite transform.

By default this transform is an identity, and not used.

See also

itk::ImageRegistrationMethodv4::SetMovingInitialTransform

Examples:

ImageRegistrationMethodDisplacement1/ImageRegistrationMethodDisplacement1.cxx.

Definition at line 159 of file sitkImageRegistrationMethod.h.

Self& itk::simple::ImageRegistrationMethod::SetOptimizerAsAmoeba	(	double	simplexDelta,
		unsigned int	numberOfIterations,
		double	parametersConvergenceTolerance = 1e-8,
		double	functionConvergenceTolerance = 1e-4,
		bool	withRestarts = false
	)

Set optimizer to Nelder-Mead downhill simplex algorithm.

See also

itk::AmoebaOptimizerv4

Self& itk::simple::ImageRegistrationMethod::SetOptimizerAsConjugateGradientLineSearch	(	double	learningRate,
		unsigned int	numberOfIterations,
		double	convergenceMinimumValue = 1e-6,
		unsigned int	convergenceWindowSize = 10,
		double	lineSearchLowerLimit = 0,
		double	lineSearchUpperLimit = 5.0,
		double	lineSearchEpsilon = 0.01,
		unsigned int	lineSearchMaximumIterations = 20,
		EstimateLearningRateType	estimateLearningRate = Once,
		double	maximumStepSizeInPhysicalUnits = 0.0
	)

Conjugate gradient descent optimizer with a golden section line search for nonlinear optimization.

See also

itk::ConjugateGradientLineSearchOptimizerv4Template

Self& itk::simple::ImageRegistrationMethod::SetOptimizerAsExhaustive	(	const std::vector< unsigned int > &	numberOfSteps,
		double	stepLength = 1.0
	)

Set the optimizer to sample the metric at regular steps.

At each iteration the GetOptimizerIteration, can be used to index into the sampling grid along with the GetCurrentMetricValue.

The resulting transform and value at the end of execution is the best location.

The OptimizerScales can be used to perform anisotropic sampling.

Note

This optimizer is not suitable for use in conjunction with the multiple scales.

See also

itk::ExhaustiveOptimizerv4

Self& itk::simple::ImageRegistrationMethod::SetOptimizerAsGradientDescent	(	double	learningRate,
		unsigned int	numberOfIterations,
		double	convergenceMinimumValue = 1e-6,
		unsigned int	convergenceWindowSize = 10,
		EstimateLearningRateType	estimateLearningRate = Once,
		double	maximumStepSizeInPhysicalUnits = 0.0
	)

Gradient descent optimizer.

See also

itk::GradientDescentOptimizerv4Template

Examples:

ImageRegistrationMethodDisplacement1/ImageRegistrationMethodDisplacement1.cxx.

Self& itk::simple::ImageRegistrationMethod::SetOptimizerAsGradientDescentLineSearch	(	double	learningRate,
		unsigned int	numberOfIterations,
		double	convergenceMinimumValue = 1e-6,
		unsigned int	convergenceWindowSize = 10,
		double	lineSearchLowerLimit = 0,
		double	lineSearchUpperLimit = 5.0,
		double	lineSearchEpsilon = 0.01,
		unsigned int	lineSearchMaximumIterations = 20,
		EstimateLearningRateType	estimateLearningRate = Once,
		double	maximumStepSizeInPhysicalUnits = 0.0
	)

Gradient descent optimizer with a golden section line search.

See also

itk::GradientDescentLineSearchOptimizerv4Template

Examples:

ImageRegistrationMethod2/ImageRegistrationMethod2.cxx.

Self& itk::simple::ImageRegistrationMethod::SetOptimizerAsLBFGSB	(	double	gradientConvergenceTolerance = 1e-5,
		unsigned int	numberOfIterations = 500,
		unsigned int	maximumNumberOfCorrections = 5,
		unsigned int	maximumNumberOfFunctionEvaluations = 2000,
		double	costFunctionConvergenceFactor = 1e+7,
		double	lowerBound = std::numeric_limits< double >::min(),
		double	upperBound = std::numeric_limits< double >::max(),
		bool	trace = false
	)

Limited memory Broyden Fletcher Goldfarb Shannon minimization with simple bounds.

The default parameters utilize LBFGSB in unbounded mode.

See also

itk::LBFGSBOptimizerv4

Examples:

ImageRegistrationMethodBSpline1/ImageRegistrationMethodBSpline1.cxx.

Self& itk::simple::ImageRegistrationMethod::SetOptimizerAsOnePlusOneEvolutionary	(	unsigned int	numberOfIterations = 100,
		double	epsilon = 1.5e-4,
		double	initialRadius = 1.01,
		double	growthFactor = -1.0,
		double	shrinkFactor = -1.0,
		unsigned int	seed = sitkWallClock
	)

1+1 evolutionary optimizer strategy.

The seed parameter is used to seed the pseudo-random number generator. If the seed parameter is 0, then the wall clock is used to seed, otherwise the fixed seed is used for reproducible behavior.

See also

itk::OnePlusOneEvolutionaryOptimizerv4

Self& itk::simple::ImageRegistrationMethod::SetOptimizerAsPowell	(	unsigned int	numberOfIterations = 100,
		unsigned int	maximumLineIterations = 100,
		double	stepLength = 1,
		double	stepTolerance = 1e-6,
		double	valueTolerance = 1e-6
	)

Powell optimization using Brent line search.

See also

itk::PowellOptimizerv4

Self& itk::simple::ImageRegistrationMethod::SetOptimizerAsRegularStepGradientDescent	(	double	learningRate,
		double	minStep,
		unsigned int	numberOfIterations,
		double	relaxationFactor = 0.5,
		double	gradientMagnitudeTolerance = 1e-4,
		EstimateLearningRateType	estimateLearningRate = Never,
		double	maximumStepSizeInPhysicalUnits = 0.0
	)

Regular Step Gradient descent optimizer.

See also

itk::RegularStepGradientDescentOptimizerv4

Examples:

ImageRegistrationMethod1/ImageRegistrationMethod1.cxx.

Self& itk::simple::ImageRegistrationMethod::SetOptimizerScales

(

const std::vector< double > &

scales

)

Manually set per parameter weighting for the transform parameters.

Self& itk::simple::ImageRegistrationMethod::SetOptimizerScalesFromIndexShift	(	unsigned int	centralRegionRadius = 5,
		double	smallParameterVariation = 0.01
	)

Estimate scales from maximum voxel shift in index space cause by parameter change.

See also

itk::RegistrationParameterScalesFromIndexShift

Self& itk::simple::ImageRegistrationMethod::SetOptimizerScalesFromJacobian

(

unsigned int

centralRegionRadius = 5

)

Estimate scales from Jacobian norms.

This scales estimator works well with versor based transforms.

See also

itk::RegistrationParameterScalesFromJacobian

Self& itk::simple::ImageRegistrationMethod::SetOptimizerScalesFromPhysicalShift	(	unsigned int	centralRegionRadius = 5,
		double	smallParameterVariation = 0.01
	)

Estimating scales of transform parameters a step sizes, from the maximum voxel shift in physical space caused by a parameter change.

See also

itk::RegistrationParameterScalesFromPhysicalShift

Examples:

ImageRegistrationMethodDisplacement1/ImageRegistrationMethodDisplacement1.cxx.

Self& itk::simple::ImageRegistrationMethod::SetOptimizerWeights

(

const std::vector< double > &

weights

)

A per parameter weighting array for the optimizer.

Allows setting of a per-local-parameter weighting array. If unset, the weights are treated as identity. Weights are multiplied by the gradient at the same time scaling is applied. Weights are similar to the scales but not estimated, and may be used, for example, to easily mask out a particular parameter during optimization to hold it constant. Or they may be used to apply another kind of prior knowledge.

Self& itk::simple::ImageRegistrationMethod::SetShrinkFactorsPerLevel

(

const std::vector< unsigned int > &

shrinkFactors

)

Set the shrink factors for each level where each level has the same shrink factor for each dimension.

See also

itk::ImageRegistrationMethodv4::SetShrinkFactorsPerLevel

Examples:

ImageRegistrationMethodDisplacement1/ImageRegistrationMethodDisplacement1.cxx.

Self& itk::simple::ImageRegistrationMethod::SetSmoothingSigmasAreSpecifiedInPhysicalUnits

(

bool

arg

)

Enable the smoothing sigmas for each level in physical units (default) or in terms of voxels.

See also

itk::ImageRegistrationMethodv4::SetSmoothingSigmasAreSpecifiedInPhysicalUnits

Self& itk::simple::ImageRegistrationMethod::SetSmoothingSigmasPerLevel

(

const std::vector< double > &

smoothingSigmas

)

Set the sigmas of Gaussian used for smoothing at each level.

See also

itk::ImageRegistrationMethodv4::SetSmoothingSigmasPerLevel

Examples:

ImageRegistrationMethodDisplacement1/ImageRegistrationMethodDisplacement1.cxx.

template<class TImageType >

void itk::simple::ImageRegistrationMethod::SetupMetric ( itk::ImageToImageMetricv4< TImageType, TImageType, TImageType, double, itk::DefaultImageToImageMetricTraitsv4< TImageType, TImageType, TImageType, double > > *  , const TImageType *  , const TImageType *    )

protected

Self& itk::simple::ImageRegistrationMethod::SetVirtualDomain	(	const std::vector< uint32_t > &	virtualSize,
		const std::vector< double > &	virtualOrigin,
		const std::vector< double > &	virtualSpacing,
		const std::vector< double > &	virtualDirection
	)

Set the virtual domain used for sampling.

Self& itk::simple::ImageRegistrationMethod::SetVirtualDomainFromImage

(

const Image &

virtualImage

)

Set the virtual domain used for sampling.

Self& itk::simple::ImageRegistrationMethod::SmoothingSigmasAreSpecifiedInPhysicalUnitsOff ( )

inline

Enable the smoothing sigmas for each level in physical units (default) or in terms of voxels.

See also

itk::ImageRegistrationMethodv4::SetSmoothingSigmasAreSpecifiedInPhysicalUnits

Definition at line 507 of file sitkImageRegistrationMethod.h.

Self& itk::simple::ImageRegistrationMethod::SmoothingSigmasAreSpecifiedInPhysicalUnitsOn ( )

inline

Enable the smoothing sigmas for each level in physical units (default) or in terms of voxels.

See also

itk::ImageRegistrationMethodv4::SetSmoothingSigmasAreSpecifiedInPhysicalUnits

Definition at line 506 of file sitkImageRegistrationMethod.h.

std::string itk::simple::ImageRegistrationMethod::ToString ( ) const

virtual

Print the information about the object to a string.

If called when the process is being executed ( during a callback ), the ITK Optimizer and Transform objects will be printed.

Reimplemented from itk::simple::ProcessObject.

Friends And Related Function Documentation

friend struct detail::MemberFunctionAddressor< MemberFunctionType >

friend

Definition at line 628 of file sitkImageRegistrationMethod.h.

Member Data Documentation

itk::ObjectToObjectOptimizerBaseTemplate<double>* itk::simple::ImageRegistrationMethod::m_ActiveOptimizer

private

Definition at line 735 of file sitkImageRegistrationMethod.h.

nsstd::auto_ptr<detail::MemberFunctionFactory<EvaluateMemberFunctionType> > itk::simple::ImageRegistrationMethod::m_EvaluateMemberFactory

private

Definition at line 630 of file sitkImageRegistrationMethod.h.

Transform itk::simple::ImageRegistrationMethod::m_FixedInitialTransform

private

Definition at line 636 of file sitkImageRegistrationMethod.h.

Transform itk::simple::ImageRegistrationMethod::m_InitialTransform

private

Definition at line 633 of file sitkImageRegistrationMethod.h.

bool itk::simple::ImageRegistrationMethod::m_InitialTransformInPlace

private

Definition at line 634 of file sitkImageRegistrationMethod.h.

InterpolatorEnum itk::simple::ImageRegistrationMethod::m_Interpolator

private

Definition at line 632 of file sitkImageRegistrationMethod.h.

unsigned int itk::simple::ImageRegistrationMethod::m_Iteration

private

Definition at line 733 of file sitkImageRegistrationMethod.h.

nsstd::auto_ptr<detail::MemberFunctionFactory<MemberFunctionType> > itk::simple::ImageRegistrationMethod::m_MemberFactory

private

Definition at line 629 of file sitkImageRegistrationMethod.h.

Image itk::simple::ImageRegistrationMethod::m_MetricFixedMaskImage

private

Definition at line 717 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_MetricIntensityDifferenceThreshold

private

Definition at line 713 of file sitkImageRegistrationMethod.h.

Image itk::simple::ImageRegistrationMethod::m_MetricMovingMaskImage

private

Definition at line 718 of file sitkImageRegistrationMethod.h.

unsigned int itk::simple::ImageRegistrationMethod::m_MetricNumberOfHistogramBins

private

Definition at line 714 of file sitkImageRegistrationMethod.h.

unsigned int itk::simple::ImageRegistrationMethod::m_MetricRadius

private

Definition at line 712 of file sitkImageRegistrationMethod.h.

std::vector<double> itk::simple::ImageRegistrationMethod::m_MetricSamplingPercentage

private

Definition at line 720 of file sitkImageRegistrationMethod.h.

unsigned int itk::simple::ImageRegistrationMethod::m_MetricSamplingSeed

private

Definition at line 722 of file sitkImageRegistrationMethod.h.

MetricSamplingStrategyType itk::simple::ImageRegistrationMethod::m_MetricSamplingStrategy

private

Definition at line 721 of file sitkImageRegistrationMethod.h.

MetricType itk::simple::ImageRegistrationMethod::m_MetricType

private

Definition at line 711 of file sitkImageRegistrationMethod.h.

bool itk::simple::ImageRegistrationMethod::m_MetricUseFixedImageGradientFilter

private

Definition at line 724 of file sitkImageRegistrationMethod.h.

bool itk::simple::ImageRegistrationMethod::m_MetricUseMovingImageGradientFilter

private

Definition at line 725 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_MetricValue

private

Definition at line 732 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_MetricVarianceForJointPDFSmoothing

private

Definition at line 715 of file sitkImageRegistrationMethod.h.

Transform itk::simple::ImageRegistrationMethod::m_MovingInitialTransform

private

Definition at line 635 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerConvergenceMinimumValue

private

Definition at line 666 of file sitkImageRegistrationMethod.h.

unsigned int itk::simple::ImageRegistrationMethod::m_OptimizerConvergenceWindowSize

private

Definition at line 667 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerCostFunctionConvergenceFactor

private

Definition at line 671 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerEpsilon

private

Definition at line 684 of file sitkImageRegistrationMethod.h.

EstimateLearningRateType itk::simple::ImageRegistrationMethod::m_OptimizerEstimateLearningRate

private

Definition at line 662 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerFunctionConvergenceTolerance

private

Definition at line 679 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerGradientConvergenceTolerance

private

Definition at line 668 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerGradientMagnitudeTolerance

private

Definition at line 665 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerGrowthFactor

private

Definition at line 686 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerInitialRadius

private

Definition at line 685 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerLearningRate

private

Definition at line 655 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerLineSearchEpsilon

private

Definition at line 660 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerLineSearchLowerLimit

private

Definition at line 658 of file sitkImageRegistrationMethod.h.

unsigned int itk::simple::ImageRegistrationMethod::m_OptimizerLineSearchMaximumIterations

private

Definition at line 661 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerLineSearchUpperLimit

private

Definition at line 659 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerLowerBound

private

Definition at line 672 of file sitkImageRegistrationMethod.h.

unsigned int itk::simple::ImageRegistrationMethod::m_OptimizerMaximumLineIterations

private

Definition at line 681 of file sitkImageRegistrationMethod.h.

unsigned int itk::simple::ImageRegistrationMethod::m_OptimizerMaximumNumberOfCorrections

private

Definition at line 669 of file sitkImageRegistrationMethod.h.

unsigned int itk::simple::ImageRegistrationMethod::m_OptimizerMaximumNumberOfFunctionEvaluations

private

Definition at line 670 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerMaximumStepSizeInPhysicalUnits

private

Definition at line 663 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerMinimumStepLength

private

Definition at line 656 of file sitkImageRegistrationMethod.h.

unsigned int itk::simple::ImageRegistrationMethod::m_OptimizerNumberOfIterations

private

Definition at line 657 of file sitkImageRegistrationMethod.h.

std::vector<unsigned int> itk::simple::ImageRegistrationMethod::m_OptimizerNumberOfSteps

private

Definition at line 675 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerParametersConvergenceTolerance

private

Definition at line 678 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerRelaxationFactor

private

Definition at line 664 of file sitkImageRegistrationMethod.h.

std::vector<double> itk::simple::ImageRegistrationMethod::m_OptimizerScales

private

Definition at line 699 of file sitkImageRegistrationMethod.h.

unsigned int itk::simple::ImageRegistrationMethod::m_OptimizerScalesCentralRegionRadius

private

Definition at line 700 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerScalesSmallParameterVariation

private

Definition at line 701 of file sitkImageRegistrationMethod.h.

OptimizerScalesType itk::simple::ImageRegistrationMethod::m_OptimizerScalesType

private

Definition at line 698 of file sitkImageRegistrationMethod.h.

unsigned int itk::simple::ImageRegistrationMethod::m_OptimizerSeed

private

Definition at line 688 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerShrinkFactor

private

Definition at line 687 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerSimplexDelta

private

Definition at line 677 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerStepLength

private

Definition at line 676 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerStepTolerance

private

Definition at line 682 of file sitkImageRegistrationMethod.h.

bool itk::simple::ImageRegistrationMethod::m_OptimizerTrace

private

Definition at line 674 of file sitkImageRegistrationMethod.h.

OptimizerType itk::simple::ImageRegistrationMethod::m_OptimizerType

private

Definition at line 654 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerUpperBound

private

Definition at line 673 of file sitkImageRegistrationMethod.h.

double itk::simple::ImageRegistrationMethod::m_OptimizerValueTolerance

private

Definition at line 683 of file sitkImageRegistrationMethod.h.

std::vector<double> itk::simple::ImageRegistrationMethod::m_OptimizerWeights

private

Definition at line 690 of file sitkImageRegistrationMethod.h.

bool itk::simple::ImageRegistrationMethod::m_OptimizerWithRestarts

private

Definition at line 680 of file sitkImageRegistrationMethod.h.

nsstd::function<unsigned int()> itk::simple::ImageRegistrationMethod::m_pfGetCurrentLevel

private

Definition at line 610 of file sitkImageRegistrationMethod.h.

nsstd::function<double()> itk::simple::ImageRegistrationMethod::m_pfGetMetricValue

private

Definition at line 605 of file sitkImageRegistrationMethod.h.

nsstd::function<double()> itk::simple::ImageRegistrationMethod::m_pfGetOptimizerConvergenceValue

private

Definition at line 604 of file sitkImageRegistrationMethod.h.

nsstd::function<unsigned int()> itk::simple::ImageRegistrationMethod::m_pfGetOptimizerIteration

private

Definition at line 601 of file sitkImageRegistrationMethod.h.

nsstd::function<double()> itk::simple::ImageRegistrationMethod::m_pfGetOptimizerLearningRate

private

Definition at line 603 of file sitkImageRegistrationMethod.h.

nsstd::function<std::vector<double>)> itk::simple::ImageRegistrationMethod::m_pfGetOptimizerPosition

private

Definition at line 602 of file sitkImageRegistrationMethod.h.

nsstd::function<std::vector<double>)> itk::simple::ImageRegistrationMethod::m_pfGetOptimizerScales

private

Definition at line 606 of file sitkImageRegistrationMethod.h.

nsstd::function<std::string()> itk::simple::ImageRegistrationMethod::m_pfGetOptimizerStopConditionDescription

private

Definition at line 607 of file sitkImageRegistrationMethod.h.

nsstd::function<void (itk::TransformBase *outTransform)> itk::simple::ImageRegistrationMethod::m_pfUpdateWithBestValue

private

Definition at line 612 of file sitkImageRegistrationMethod.h.

std::vector<unsigned int> itk::simple::ImageRegistrationMethod::m_ShrinkFactorsPerLevel

private

Definition at line 727 of file sitkImageRegistrationMethod.h.

bool itk::simple::ImageRegistrationMethod::m_SmoothingSigmasAreSpecifiedInPhysicalUnits

private

Definition at line 729 of file sitkImageRegistrationMethod.h.

std::vector<double> itk::simple::ImageRegistrationMethod::m_SmoothingSigmasPerLevel

private

Definition at line 728 of file sitkImageRegistrationMethod.h.

std::string itk::simple::ImageRegistrationMethod::m_StopConditionDescription

private

Definition at line 731 of file sitkImageRegistrationMethod.h.

std::vector<double> itk::simple::ImageRegistrationMethod::m_VirtualDomainDirection

private

Definition at line 641 of file sitkImageRegistrationMethod.h.

std::vector<double> itk::simple::ImageRegistrationMethod::m_VirtualDomainOrigin

private

Definition at line 639 of file sitkImageRegistrationMethod.h.

std::vector<uint32_t> itk::simple::ImageRegistrationMethod::m_VirtualDomainSize

private

Definition at line 638 of file sitkImageRegistrationMethod.h.

std::vector<double> itk::simple::ImageRegistrationMethod::m_VirtualDomainSpacing

private

Definition at line 640 of file sitkImageRegistrationMethod.h.

---

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

• sitkImageRegistrationMethod.h