Computes similarity between two objects to be registered. More...

#include <itkMatchCardinalityImageToImageMetric.h>

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

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

Classes
struct	ThreadStruct
Public Types
typedef SmartPointer< const Self >	ConstPointer
typedef Superclass::DerivativeType	DerivativeType
typedef Superclass::FixedImageConstPointer	FixedImageConstPointer
typedef Superclass::FixedImageRegionType	FixedImageRegionType
typedef Superclass::FixedImageType	FixedImageType
typedef Superclass::GradientPixelType	GradientPixelType
typedef Superclass::MeasureType	MeasureType
typedef Superclass::MovingImageConstPointer	MovingImageConstPointer
typedef Superclass::MovingImageType	MovingImageType
typedef SmartPointer< Self >	Pointer
typedef Superclass::RealType	RealType
typedef MatchCardinalityImageToImageMetric	Self
typedef ImageToImageMetric < TFixedImage, TMovingImage >	Superclass
typedef Superclass::TransformJacobianType	TransformJacobianType
typedef Superclass::TransformParametersType	TransformParametersType
typedef Superclass::TransformPointer	TransformPointer
typedef Superclass::TransformType	TransformType
Public Member Functions
virtual ::itk::LightObject::Pointer	CreateAnother (void) const
virtual const char *	GetNameOfClass () const
MeasureType	GetValue (const TransformParametersType &parameters) const

void	GetDerivative (const TransformParametersType &, DerivativeType &derivative) const

virtual void	SetMeasureMatches (bool _arg)
virtual void	MeasureMatchesOn ()
virtual void	MeasureMatchesOff ()
virtual bool	GetMeasureMatches () const
Static Public Member Functions
static Pointer	New ()
Protected Member Functions
MeasureType	GetNonconstValue (const TransformParametersType &parameters)
virtual ThreadIdType	SplitFixedRegion (ThreadIdType i, int num, FixedImageRegionType &splitRegion)
virtual void	ThreadedGetValue (const FixedImageRegionType &outputRegionForThread, ThreadIdType threadId)
Static Protected Member Functions
static ITK_THREAD_RETURN_TYPE	ThreaderCallback (void *arg)
Private Member Functions

	MatchCardinalityImageToImageMetric (const Self &)
void	operator= (const Self &)
Private Attributes
bool	m_MeasureMatches
std::vector< SizeValueType >	m_ThreadCounts
MultiThreader::Pointer	m_Threader
std::vector< MeasureType >	m_ThreadMatches
MultiThreader *	GetMultiThreader ()
	MatchCardinalityImageToImageMetric ()
virtual	~MatchCardinalityImageToImageMetric ()
void	PrintSelf (std::ostream &os, Indent indent) const

Detailed Description

template<class TFixedImage, class TMovingImage>
class itk::MatchCardinalityImageToImageMetric< TFixedImage, TMovingImage >

Computes similarity between two objects to be registered.

This Class is templated over the type of the fixed and moving images to be compared.

This metric computes cardinality of the set of pixels that match exactly between the moving and fixed images. The spatial correspondance between both images is established through a Transform. Pixel values are taken from the Moving image. Their positions are mapped to the Fixed image and result in general in non-grid position on it. Values at these non-grid position of the Fixed image are interpolated using a user-selected Interpolator.

This metric is designed for matching label maps. All pixel mismatches are considered equal whether they are between label 1 and label 2 or between label 1 and label 500. In other words, the magnitude of an individual label mismatch is not relevant, or the occurence of a label mismatch is important.

Given the nature of label maps, a nearest neighbor interpolator is the preferred interpolator.

The metric measure can measure the number of pixel matches (pixels with exactly the same label) or pixel mismatches (pixels with different labels). The returned metric value is the number of pixel matches (or mismatches) normalized by the number of pixels considered. The number of pixel considered is a function of the number of pixels in the overlap of the fixed and moving image buffers conditional on any assigned masks.

Definition at line 67 of file itkMatchCardinalityImageToImageMetric.h.