ITK  4.0.0
Insight Segmentation and Registration Toolkit
Public Types | Public Member Functions | Protected Member Functions | Private Member Functions | Private Attributes
itk::Statistics::GaussianMembershipFunction< TMeasurementVector > Class Template Reference

GaussianMembershipFunction models class membership through a multivariate Gaussian function. More...

#include <itkGaussianMembershipFunction.h>

Inheritance diagram for itk::Statistics::GaussianMembershipFunction< TMeasurementVector >:
Collaboration diagram for itk::Statistics::GaussianMembershipFunction< TMeasurementVector >:

List of all members.

Public Types

typedef SmartPointer< const SelfConstPointer
typedef VariableSizeMatrix
< double > 
CovarianceMatrixType
typedef MeasurementVectorRealType MeanVectorType
typedef itk::NumericTraits
< MeasurementVectorType >
::RealType 
MeasurementVectorRealType
typedef
Superclass::MeasurementVectorSizeType 
MeasurementVectorSizeType
typedef TMeasurementVector MeasurementVectorType
typedef Superclass::Pointer MembershipFunctionPointer
typedef SmartPointer< SelfPointer
typedef GaussianMembershipFunction Self
typedef MembershipFunctionBase
< TMeasurementVector > 
Superclass

Public Member Functions

MembershipFunctionPointer Clone () const
double Evaluate (const MeasurementVectorType &measurement) const
virtual const
CovarianceMatrixType
GetCovariance ()
virtual const
CovarianceMatrixType
GetInverseCovariance ()
virtual const MeanVectorTypeGetMean ()
void SetCovariance (const CovarianceMatrixType &cov)
void SetMean (const MeanVectorType &mean)

Protected Member Functions

 GaussianMembershipFunction (void)
void PrintSelf (std::ostream &os, Indent indent) const
virtual ~GaussianMembershipFunction (void)

Private Member Functions

 GaussianMembershipFunction (const Self &)
void operator= (const Self &)

Private Attributes

CovarianceMatrixType m_Covariance
bool m_CovarianceNonsingular
CovarianceMatrixType m_InverseCovariance
MeanVectorType m_Mean
double m_PreFactor
virtual const char * GetNameOfClass () const
virtual ::itk::LightObject::Pointer CreateAnother (void) const
static Pointer New ()

Detailed Description

template<class TMeasurementVector>
class itk::Statistics::GaussianMembershipFunction< TMeasurementVector >

GaussianMembershipFunction models class membership through a multivariate Gaussian function.

GaussianMembershipFunction is a subclass of MembershipFunctionBase that models class membership (or likelihood) using a multivariate Gaussian function. The mean and covariance structure of the Gaussian are established using the methods SetMean() and SetCovariance(). The mean is a vector-type that is the same vector-type as the measurement vector but guarenteed to have a real element type. For instance, if the measurement type is an Vector<int,3>, then the mean is Vector<double,3>. If the measurement type is a VariableLengthVector<float>, then the mean is VariableLengthVector<double>. In contrast to this behavior, the covariance is always a VariableSizeMatrix<double>.

If the covariance is singular or nearly singular, the membership function behaves somewhat like an impulse located at the mean. In this case, we specify the covariance to be a diagonal matrix with large values along the diagonal. This membership function, therefore, will return small but differentiable values everywher and increase sharply near the mean.

Definition at line 55 of file itkGaussianMembershipFunction.h.


Member Typedef Documentation

template<class TMeasurementVector >
typedef SmartPointer< const Self > itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::ConstPointer
template<class TMeasurementVector >
typedef VariableSizeMatrix< double > itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::CovarianceMatrixType

Type of the covariance matrix

Definition at line 85 of file itkGaussianMembershipFunction.h.

template<class TMeasurementVector >
typedef MeasurementVectorRealType itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::MeanVectorType

Definition at line 82 of file itkGaussianMembershipFunction.h.

template<class TMeasurementVector >
typedef itk::NumericTraits< MeasurementVectorType >::RealType itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::MeasurementVectorRealType

Type of the mean vector. RealType on a vector-type is the same vector-type but with a real element type.

Definition at line 81 of file itkGaussianMembershipFunction.h.

template<class TMeasurementVector >
typedef Superclass::MeasurementVectorSizeType itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::MeasurementVectorSizeType

Length of each measurement vector

Reimplemented from itk::Statistics::MembershipFunctionBase< TMeasurementVector >.

Definition at line 77 of file itkGaussianMembershipFunction.h.

template<class TMeasurementVector >
typedef TMeasurementVector itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::MeasurementVectorType

Typedef alias for the measurement vectors

Reimplemented from itk::Statistics::MembershipFunctionBase< TMeasurementVector >.

Definition at line 74 of file itkGaussianMembershipFunction.h.

template<class TMeasurementVector >
typedef Superclass::Pointer itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::MembershipFunctionPointer

SmartPointer class for superclass

Definition at line 67 of file itkGaussianMembershipFunction.h.

template<class TMeasurementVector >
typedef SmartPointer< Self > itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::Pointer
template<class TMeasurementVector >
typedef GaussianMembershipFunction itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::Self

Standard class typedefs

Reimplemented from itk::Statistics::MembershipFunctionBase< TMeasurementVector >.

Definition at line 60 of file itkGaussianMembershipFunction.h.

template<class TMeasurementVector >
typedef MembershipFunctionBase< TMeasurementVector > itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::Superclass

Constructor & Destructor Documentation

template<class TMeasurementVector >
itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::GaussianMembershipFunction ( void  ) [protected]
template<class TMeasurementVector >
virtual itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::~GaussianMembershipFunction ( void  ) [inline, protected, virtual]

Definition at line 119 of file itkGaussianMembershipFunction.h.

template<class TMeasurementVector >
itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::GaussianMembershipFunction ( const Self ) [private]

Member Function Documentation

template<class TMeasurementVector >
MembershipFunctionPointer itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::Clone ( ) const [virtual]

Method to clone a membership function, i.e. create a new instance of the same type of membership function and configure its ivars to match.

Implements itk::Statistics::MembershipFunctionBase< TMeasurementVector >.

template<class TMeasurementVector >
virtual::itk::LightObject::Pointer itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::CreateAnother ( void  ) const [virtual]

Standard macros

Reimplemented from itk::Object.

template<class TMeasurementVector >
double itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::Evaluate ( const MeasurementVectorType measurement) const [virtual]

Evaluate the probability density of a measurement vector.

Implements itk::Statistics::MembershipFunctionBase< TMeasurementVector >.

template<class TMeasurementVector >
virtual const CovarianceMatrixType& itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::GetCovariance ( ) [virtual]
template<class TMeasurementVector >
virtual const CovarianceMatrixType& itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::GetInverseCovariance ( ) [virtual]
template<class TMeasurementVector >
virtual const MeanVectorType& itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::GetMean ( ) [virtual]

Get the mean of the Gaussian distribution. Mean is a vector type similar to the measurement type but with a real element type.

template<class TMeasurementVector >
virtual const char* itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::GetNameOfClass ( ) const [virtual]
template<class TMeasurementVector >
static Pointer itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::New ( ) [static]

Standard macros

Reimplemented from itk::Object.

template<class TMeasurementVector >
void itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::operator= ( const Self ) [private]

Mutex lock to protect modification to the reference count

Reimplemented from itk::Statistics::MembershipFunctionBase< TMeasurementVector >.

template<class TMeasurementVector >
void itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::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::Statistics::MembershipFunctionBase< TMeasurementVector >.

template<class TMeasurementVector >
void itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::SetCovariance ( const CovarianceMatrixType cov)

Set the covariance matrix. Covariance matrix is a VariableSizeMatrix of doubles. The inverse of the covariance matrix and the normlization term for the multivariate Gaussian are calculate whenever the covaraince matrix is changed.

template<class TMeasurementVector >
void itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::SetMean ( const MeanVectorType mean)

Set the mean of the Gaussian distribution. Mean is a vector type similar to the measurement type but with a real element type.


Member Data Documentation

template<class TMeasurementVector >
CovarianceMatrixType itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::m_Covariance [private]

Definition at line 127 of file itkGaussianMembershipFunction.h.

template<class TMeasurementVector >
bool itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::m_CovarianceNonsingular [private]

Boolean to cache whether the covarinace is singular or nearly singular

Definition at line 138 of file itkGaussianMembershipFunction.h.

template<class TMeasurementVector >
CovarianceMatrixType itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::m_InverseCovariance [private]

Definition at line 131 of file itkGaussianMembershipFunction.h.

template<class TMeasurementVector >
MeanVectorType itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::m_Mean [private]

Definition at line 126 of file itkGaussianMembershipFunction.h.

template<class TMeasurementVector >
double itk::Statistics::GaussianMembershipFunction< TMeasurementVector >::m_PreFactor [private]

Definition at line 135 of file itkGaussianMembershipFunction.h.


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