#include <itkCumulativeGaussianOptimizer.h>

Inheritance diagram for itk::CumulativeGaussianOptimizer:

Collaboration diagram for itk::CumulativeGaussianOptimizer:

Public Types
typedef SmartPointer< const Self >	ConstPointer
typedef CumulativeGaussianCostFunction	CostFunctionType
typedef CostFunctionType::MeasureType	MeasureType
typedef SmartPointer< Self >	Pointer
typedef CumulativeGaussianOptimizer	Self
typedef MultipleValuedNonLinearOptimizer	Superclass
Public Member Functions
virtual ::itk::LightObject::Pointer	CreateAnother (void) const
virtual const char *	GetNameOfClass () const
const std::string	GetStopConditionDescription () const
void	PrintArray (MeasureType *array)
void	SetDataArray (MeasureType *dataArray)
void	StartOptimization ()

virtual void	SetDifferenceTolerance (double _arg)
virtual void	SetVerbose (bool _arg)
virtual double	GetComputedMean ()
virtual double	GetComputedStandardDeviation ()
virtual double	GetUpperAsymptote ()
virtual double	GetLowerAsymptote ()
virtual MeasureType *	GetFinalSampledArray ()
virtual double	GetFitError ()
Static Public Member Functions
static Pointer	New ()
Protected Member Functions
	CumulativeGaussianOptimizer ()
void	PrintSelf (std::ostream &os, Indent indent) const
virtual	~CumulativeGaussianOptimizer ()
Private Member Functions
MeasureType *	ExtendGaussian (MeasureType originalArray, MeasureType extendedArray, int startingPointForInsertion)
double	FindAverageSumOfSquaredDifferences (MeasureType array1, MeasureType array2)
void	FindParametersOfGaussian (MeasureType *sampledGaussianArray)
void	MeasureGaussianParameters (MeasureType *array)
void	PrintComputedParameterHeader ()
void	PrintComputedParameters ()
MeasureType *	RecalculateExtendedArrayFromGaussianParameters (MeasureType originalArray, MeasureType extendedArray, int startingPointForInsertion)
double	VerticalBestShift (MeasureType originalArray, MeasureType newArray)
Private Attributes
double	m_ComputedAmplitude
double	m_ComputedMean
double	m_ComputedStandardDeviation
double	m_ComputedTransitionHeight
MeasureType *	m_CumulativeGaussianArray
double	m_DifferenceTolerance
MeasureType *	m_FinalSampledArray
double	m_FitError
double	m_LowerAsymptote
double	m_OffsetForMean
std::ostringstream	m_StopConditionDescription
double	m_UpperAsymptote
bool	m_Verbose

Detailed Description

This is an optimizer specific to estimating the parameters of Cumulative Gaussian sampled data.

This optimizer will only work if the data array is sampled from a Cumulative Gaussian curve. It's more of a curve fitter than an optimizer, with the advantage of being fast and specific. It works by taking the derivative of the Cumulative Gaussian sample then repeatedly extending the tails of the Gaussian and recalculating the Gaussian parameters until the change in iterations is within tolerance or very small. The Gaussian is then integrated to reproduce the Cumulative Gaussian and the asymptotes are estimated by using least squares fit to estimate the constant from integration.

Definition at line 47 of file itkCumulativeGaussianOptimizer.h.

Member Typedef Documentation

typedef SmartPointer< const Self > itk::CumulativeGaussianOptimizer::ConstPointer

Reimplemented from itk::MultipleValuedNonLinearOptimizer.

Definition at line 56 of file itkCumulativeGaussianOptimizer.h.

typedef CumulativeGaussianCostFunction itk::CumulativeGaussianOptimizer::CostFunctionType

Cost function typedef. NOTE: This optimizer is specific to fitting a Cumulative Gaussian.

Reimplemented from itk::MultipleValuedNonLinearOptimizer.

Definition at line 60 of file itkCumulativeGaussianOptimizer.h.

typedef CostFunctionType::MeasureType itk::CumulativeGaussianOptimizer::MeasureType

Data array typedef.

Reimplemented from itk::MultipleValuedNonLinearOptimizer.

Definition at line 63 of file itkCumulativeGaussianOptimizer.h.

typedef SmartPointer< Self > itk::CumulativeGaussianOptimizer::Pointer

Reimplemented from itk::MultipleValuedNonLinearOptimizer.

Definition at line 55 of file itkCumulativeGaussianOptimizer.h.

typedef CumulativeGaussianOptimizer itk::CumulativeGaussianOptimizer::Self

Standard typedefs.

Reimplemented from itk::MultipleValuedNonLinearOptimizer.

Definition at line 53 of file itkCumulativeGaussianOptimizer.h.

typedef MultipleValuedNonLinearOptimizer itk::CumulativeGaussianOptimizer::Superclass

Reimplemented from itk::MultipleValuedNonLinearOptimizer.

Definition at line 54 of file itkCumulativeGaussianOptimizer.h.

Constructor & Destructor Documentation

itk::CumulativeGaussianOptimizer::CumulativeGaussianOptimizer ( ) [protected]

virtual itk::CumulativeGaussianOptimizer::~CumulativeGaussianOptimizer ( ) [protected, virtual]

Member Function Documentation

virtual::itk::LightObject::Pointer itk::CumulativeGaussianOptimizer::CreateAnother ( void ) const [virtual]

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::MultipleValuedNonLinearOptimizer.

MeasureType* itk::CumulativeGaussianOptimizer::ExtendGaussian	(	MeasureType *	originalArray,
		MeasureType *	extendedArray,
		int	startingPointForInsertion
	)		`[private]`

Extend the tails of the Gaussian.

double itk::CumulativeGaussianOptimizer::FindAverageSumOfSquaredDifferences	(	MeasureType *	array1,
		MeasureType *	array2
	)		`[private]`

Calculates the squared difference error between each Gaussian iteration loop.

void itk::CumulativeGaussianOptimizer::FindParametersOfGaussian ( MeasureType * sampledGaussianArray ) [private]

Given an array sampled from a Gaussin, compute the final parameters.

virtual double itk::CumulativeGaussianOptimizer::GetComputedMean ( ) [virtual]

Set and get macros.

virtual double itk::CumulativeGaussianOptimizer::GetComputedStandardDeviation ( ) [virtual]

Set and get macros.

virtual MeasureType* itk::CumulativeGaussianOptimizer::GetFinalSampledArray ( ) [virtual]

Set and get macros.

virtual double itk::CumulativeGaussianOptimizer::GetFitError ( ) [virtual]

Set and get macros.

virtual double itk::CumulativeGaussianOptimizer::GetLowerAsymptote ( ) [virtual]

Set and get macros.

virtual const char* itk::CumulativeGaussianOptimizer::GetNameOfClass ( ) const [virtual]

Run-time type information (and related methods).

Reimplemented from itk::MultipleValuedNonLinearOptimizer.

const std::string itk::CumulativeGaussianOptimizer::GetStopConditionDescription ( ) const [virtual]

Report the reason for stopping.

Reimplemented from itk::Optimizer.

virtual double itk::CumulativeGaussianOptimizer::GetUpperAsymptote ( ) [virtual]

Set and get macros.

void itk::CumulativeGaussianOptimizer::MeasureGaussianParameters ( MeasureType * array ) [private]

Measure the parameters of a Gaussian sampled array.

static Pointer itk::CumulativeGaussianOptimizer::New ( ) [static]

Method for creation through the object factory.

Reimplemented from itk::MultipleValuedNonLinearOptimizer.

void itk::CumulativeGaussianOptimizer::PrintArray ( MeasureType * array )

Print an array.

void itk::CumulativeGaussianOptimizer::PrintComputedParameterHeader ( ) [private]

Print the header for output table.

void itk::CumulativeGaussianOptimizer::PrintComputedParameters ( ) [private]

Print the computed parameters.

void itk::CumulativeGaussianOptimizer::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::MultipleValuedNonLinearOptimizer.

MeasureType* itk::CumulativeGaussianOptimizer::RecalculateExtendedArrayFromGaussianParameters	(	MeasureType *	originalArray,
		MeasureType *	extendedArray,
		int	startingPointForInsertion
	)		`[private]`