Multiple valley shaped curve function. More...

#include <itkCompositeValleyFunction.h>

Inheritance diagram for itk::CompositeValleyFunction:

Collaboration diagram for itk::CompositeValleyFunction:

Public Types
typedef Superclass::MeasureArrayType	MeasureArrayType
typedef Superclass::MeasureType	MeasureType
typedef CacheableScalarFunction	Superclass
Public Member Functions
	CompositeValleyFunction (const MeasureArrayType &classMeans, const MeasureArrayType &classSigmas)
MeasureType	Evaluate (MeasureType x)
double	GetCacheLowerBound ()
double	GetCacheUpperBound ()
double	GetInterval ()
double	GetLowerBound ()
long	GetNumberOfSamples ()
double	GetUpperBound ()
bool	IsCacheAvailable ()
MeasureType	operator() (MeasureType x)
MeasureType	valley (MeasureType d)
virtual	~CompositeValleyFunction ()


MeasureType	GetCachedValue (MeasureType x)
Protected Member Functions
void	AddNewClass (double mean, double sigma)
void	CreateCache (double lowerBound, double upperBound, long sampleSize)
void	Initialize ()

Detailed Description

Multiple valley shaped curve function.

Its functional form f(x) is : sum (valley( (x - mean[i]) / sigma[i] ) ) over i from 0 to the number of target classes where valley(x) = 1 - 1 / (1 + x^2 / 3)

The plotting of the function return shows multiple lowest points at each mean[i] position. There are two more important shape parameters for this function, higher-bound and lower-bound. Upper-bound will be highest mean value among target classes' means + its sigma value * 9, and lower-bound will be lowest mean value among target classes' means - its sigma value * 9

For example, if there are two target classes with their means at 4 and 6. The plotting may look like the following:

| |********* ****** | * * | * * * | * * * * | * * * * | * * * * | * * ---+-----+------*------*------- | 2 4 6 |

This is a part of the bias correction methods and implementaion that was initially developed and implemented by Martin Styner, Univ. of North Carolina at Chapel Hill, and his colleagues.

For more details. refer to the following articles. "Parametric estimate of intensity inhomogeneities applied to MRI" Martin Styner, G. Gerig, Christian Brechbuehler, Gabor Szekely, IEEE TRANSACTIONS ON MEDICAL IMAGING; 19(3), pp. 153-165, 2000, (http://www.cs.unc.edu/~styner/docs/tmi00.pdf)

"Evaluation of 2D/3D bias correction with 1+1ES-optimization" Martin Styner, Prof. Dr. G. Gerig (IKT, BIWI, ETH Zuerich), TR-197 (http://www.cs.unc.edu/~styner/docs/StynerTR97.pdf)

Definition at line 96 of file itkCompositeValleyFunction.h.

Member Typedef Documentation

typedef Superclass::MeasureArrayType itk::CompositeValleyFunction::MeasureArrayType

Reimplemented from itk::CacheableScalarFunction.

Definition at line 105 of file itkCompositeValleyFunction.h.

typedef Superclass::MeasureType itk::CompositeValleyFunction::MeasureType

Cost value type.

Reimplemented from itk::CacheableScalarFunction.

Definition at line 104 of file itkCompositeValleyFunction.h.

typedef CacheableScalarFunction itk::CompositeValleyFunction::Superclass

Superclass to this class.

Definition at line 101 of file itkCompositeValleyFunction.h.

Constructor & Destructor Documentation

itk::CompositeValleyFunction::CompositeValleyFunction	(	const MeasureArrayType &	classMeans,
		const MeasureArrayType &	classSigmas
	)

Constructor.

virtual itk::CompositeValleyFunction::~CompositeValleyFunction ( ) [inline, virtual]

Destructor.

Definition at line 112 of file itkCompositeValleyFunction.h.

Member Function Documentation

void itk::CompositeValleyFunction::AddNewClass	(	double	mean,
		double	sigma
	)			`[inline, protected]`

Definition at line 160 of file itkCompositeValleyFunction.h.

void itk::CacheableScalarFunction::CreateCache	(	double	lowerBound,
		double	upperBound,
		long	sampleSize
	)			`[protected, inherited]`

Create the internal cache table and fill it with pre-evaluated values.

MeasureType itk::CompositeValleyFunction::Evaluate ( MeasureType x ) [inline, virtual]

Evalaute the function at point x.

Reimplemented from itk::CacheableScalarFunction.

Definition at line 140 of file itkCompositeValleyFunction.h.

References valley().

Referenced by operator()().

MeasureType itk::CacheableScalarFunction::GetCachedValue ( MeasureType x ) [inline, inherited]

y = f(x) = (approximately) cache_table(index(x)) Get the function return using the internal cache table NOTE: Since the index calculation needs conversion from double to int, truncation happens. As a result, the return values from Evaluate(x) and GetCachedValue(x) may not be same for the same x.

Definition at line 96 of file itkCacheableScalarFunction.h.

Referenced by operator()().

double itk::CacheableScalarFunction::GetCacheLowerBound ( ) [inline, inherited]

Get the lower-bound of domain that is used for filling the cache table.

Definition at line 79 of file itkCacheableScalarFunction.h.

double itk::CacheableScalarFunction::GetCacheUpperBound ( ) [inline, inherited]

Get the upper-bound of domain that is used for filling the cache table.

Definition at line 76 of file itkCacheableScalarFunction.h.

double itk::CacheableScalarFunction::GetInterval ( ) [inline, inherited]

Gets the interval of each cell between the upper and lower bound

Definition at line 88 of file itkCacheableScalarFunction.h.

double itk::CompositeValleyFunction::GetLowerBound ( ) [inline]