Base class for Image Registration Methods. More...

#include <itkImageRegistrationMethod.h>

Inheritance diagram for itk::ImageRegistrationMethod< TFixedImage, TMovingImage >:

Collaboration diagram for itk::ImageRegistrationMethod< TFixedImage, TMovingImage >:

Public Types
typedef SmartPointer< const Self >	ConstPointer
typedef DataObject::Pointer	DataObjectPointer
typedef ProcessObject::DataObjectPointerArraySizeType	DataObjectPointerArraySizeType
typedef FixedImageType::ConstPointer	FixedImageConstPointer
typedef MetricType::FixedImageRegionType	FixedImageRegionType
typedef TFixedImage	FixedImageType
typedef InterpolatorType::Pointer	InterpolatorPointer
typedef MetricType::InterpolatorType	InterpolatorType
typedef MetricType::Pointer	MetricPointer
typedef ImageToImageMetric < FixedImageType, MovingImageType >	MetricType
typedef MovingImageType::ConstPointer	MovingImageConstPointer
typedef TMovingImage	MovingImageType
typedef SingleValuedNonLinearOptimizer	OptimizerType
typedef MetricType::TransformParametersType	ParametersType
typedef SmartPointer< Self >	Pointer
typedef ImageRegistrationMethod	Self
typedef ProcessObject	Superclass
typedef TransformOutputType::ConstPointer	TransformOutputConstPointer
typedef TransformOutputType::Pointer	TransformOutputPointer
typedef DataObjectDecorator < TransformType >	TransformOutputType
typedef TransformType::Pointer	TransformPointer
typedef MetricType::TransformType	TransformType
Public Member Functions
virtual ::itk::LightObject::Pointer	CreateAnother (void) const
virtual const FixedImageType *	GetFixedImage ()
virtual const FixedImageRegionType &	GetFixedImageRegion ()
virtual bool	GetFixedImageRegionDefined () const
virtual const ParametersType &	GetInitialTransformParameters ()
virtual const ParametersType &	GetLastTransformParameters ()
virtual const MovingImageType *	GetMovingImage ()
unsigned long	GetMTime () const
virtual const char *	GetNameOfClass () const
const TransformOutputType *	GetOutput () const
virtual void	Initialize () throw ( ExceptionObject )
virtual DataObjectPointer	MakeOutput (DataObjectPointerArraySizeType idx)
void	SetFixedImage (const FixedImageType *fixedImage)
void	SetFixedImageRegion (const FixedImageRegionType &region)
virtual void	SetFixedImageRegionDefined (bool _arg)
virtual void	SetInitialTransformParameters (const ParametersType &param)
void	SetMovingImage (const MovingImageType *movingImage)

virtual void	SetOptimizer (OptimizerType *_arg)
virtual OptimizerType *	GetOptimizer ()

virtual void	SetMetric (MetricType *_arg)
virtual MetricType *	GetMetric ()

virtual void	SetTransform (TransformType *_arg)
virtual TransformType *	GetTransform ()

virtual void	SetInterpolator (InterpolatorType *_arg)
virtual InterpolatorType *	GetInterpolator ()
Static Public Member Functions
static Pointer	New ()
Protected Member Functions
void	GenerateData ()
	ImageRegistrationMethod ()
void	PrintSelf (std::ostream &os, Indent indent) const
virtual void	SetLastTransformParameters (ParametersType _arg)
void	StartOptimization (void)
void	StartRegistration (void)
virtual	~ImageRegistrationMethod ()
Private Member Functions
	ImageRegistrationMethod (const Self &)
void	operator= (const Self &)
Private Attributes
FixedImageConstPointer	m_FixedImage
FixedImageRegionType	m_FixedImageRegion
bool	m_FixedImageRegionDefined
ParametersType	m_InitialTransformParameters
InterpolatorPointer	m_Interpolator
ParametersType	m_LastTransformParameters
MetricPointer	m_Metric
MovingImageConstPointer	m_MovingImage
OptimizerType::Pointer	m_Optimizer
TransformPointer	m_Transform

Detailed Description

template<typename TFixedImage, typename TMovingImage>
class itk::ImageRegistrationMethod< TFixedImage, TMovingImage >

Base class for Image Registration Methods.

This Class define the generic interface for a registration method.

This class is templated over the type of the two image to be registered. A generic Transform is used by this class. That allows to select at run time the particular type of transformation that is to be applied for registering the images.

This method use a generic Metric in order to compare the two images. the final goal of the registration method is to find the set of parameters of the Transformation that optimizes the metric.

The registration method also support a generic optimizer that can be selected at run-time. The only restriction for the optimizer is that it should be able to operate in single-valued cost functions given that the metrics used to compare images provide a single value as output.

The terms : Fixed image and Moving image are used in this class to indicate what image is being mapped by the transform.

This class uses the coordinate system of the Fixed image as a reference and searchs for a Transform that will map points from the space of the Fixed image to the space of the Moving image.

For doing so, a Metric will be continously applied to compare the Fixed image with the Transformed Moving image. This process also requires to interpolate values from the Moving image.

Wiki Examples:

All Examples

A basic global registration of two images

A global registration of two images

A global registration of two images

Definition at line 70 of file itkImageRegistrationMethod.h.