#include <itkBayesianClassifierInitializationImageFilter.h>

Inheritance diagram for itk::BayesianClassifierInitializationImageFilter< TInputImage, TProbabilityPrecisionType >:

Collaboration diagram for itk::BayesianClassifierInitializationImageFilter< TInputImage, TProbabilityPrecisionType >:

Public Types
typedef SmartPointer< const Self >	ConstPointer
typedef ImageRegionConstIterator < InputImageType >	InputImageIteratorType
typedef TInputImage	InputImageType
typedef InputImageType::PixelType	InputPixelType
typedef Vector< InputPixelType, 1 >	MeasurementVectorType
typedef MembershipFunctionContainerType::Pointer	MembershipFunctionContainerPointer
typedef VectorContainer < unsigned int, MembershipFunctionPointer >	MembershipFunctionContainerType
typedef MembershipFunctionType::Pointer	MembershipFunctionPointer
typedef Statistics::MembershipFunctionBase < MeasurementVectorType >	MembershipFunctionType
typedef ImageRegionIterator < MembershipImageType >	MembershipImageIteratorType
typedef MembershipImageType::Pointer	MembershipImagePointer
typedef VectorImage < ProbabilityPrecisionType, itkGetStaticConstMacro(Dimension) >	MembershipImageType
typedef MembershipImageType::PixelType	MembershipPixelType
typedef VectorImage < ProbabilityPrecisionType, itkGetStaticConstMacro(Dimension) >	OutputImageType
typedef OutputImageType::PixelType	OutputPixelType
typedef SmartPointer< Self >	Pointer
typedef TProbabilityPrecisionType	ProbabilityPrecisionType
typedef BayesianClassifierInitializationImageFilter	Self
typedef ImageToImageFilter < InputImageType, OutputImageType >	Superclass
Public Member Functions
virtual ::itk::LightObject::Pointer	CreateAnother (void) const
virtual void	GenerateOutputInformation ()
virtual MembershipFunctionContainerType *	GetMembershipFunctionContainer ()
virtual const char *	GetNameOfClass () const
virtual void	SetMembershipFunctions (MembershipFunctionContainerType *densityFunctionContainer)
	typedef (Concept::MultiplyOperator< InputPixelType >) InputMultiplyOperatorCheck
	typedef (Concept::Convertible< double, TProbabilityPrecisionType >) DoubleConvertibleToProbabilityCheck
	typedef (Concept::HasNumericTraits< InputPixelType >) InputHasNumericTraitsCheck
	typedef (Concept::HasNumericTraits< TProbabilityPrecisionType >) ProbabilityHasNumericTraitsCheck
	typedef (Concept::AdditiveOperators< double, InputPixelType >) DoublePlusInputCheck

virtual void	SetNumberOfClasses (unsigned int _arg)
virtual unsigned int	GetNumberOfClasses () const
Static Public Member Functions
static Pointer	New ()
Static Public Attributes
static const unsigned int	Dimension = ::itk::GetImageDimension< InputImageType >::ImageDimension
Protected Member Functions
virtual void	GenerateData ()
virtual void	InitializeMembershipFunctions ()

	BayesianClassifierInitializationImageFilter ()
virtual	~BayesianClassifierInitializationImageFilter ()
void	PrintSelf (std::ostream &os, Indent indent) const
Private Member Functions
	BayesianClassifierInitializationImageFilter (const Self &)
void	operator= (const Self &)
Private Attributes
MembershipFunctionContainerType::Pointer	m_MembershipFunctionContainer
unsigned int	m_NumberOfClasses
bool	m_UserSuppliesMembershipFunctions

Detailed Description

template<class TInputImage, class TProbabilityPrecisionType = float>
class itk::BayesianClassifierInitializationImageFilter< TInputImage, TProbabilityPrecisionType >

This filter is intended to be used as a helper class to initialize the BayesianClassifierImageFilter.

: The goal of this filter is to generate a membership image that indicates the membership of each pixel to each class. These membership images are fed as input to the Bayesian classfier filter.

Parameters: Number of classes: This defines the number of classes, which will determine the number of membership images that will be generated. The user must specify this.

: Membership functions: The user can optionally plugin in any membership function. The number of membership functions plugged in should be the same as the number of classes. If the user does not supply membership functions, the filter will generate membership functions for you. These functions are Gaussian density functions centered around 'n' pixel intensity values, . These 'n' values are obtained by running K-means on the image. In other words, the default behaviour of the filter is to generate Gaussian mixture model for the input image.

Inputs and Outputs: The filter takes a scalar Image as input and generates a VectorImage, each component of which represents memberships of each pixel to the class .

Template parameters: This filter is templated over the input image type and the data type used to represent the probabilities (defaults to float).

Author:: John Melonakos, Georgia Tech

Note:: This work is part of the National Alliance for Medical Image Computing (NAMIC), funded by the National Institutes of Health through the NIH Roadmap for Medical Research, Grant U54 EB005149.

See also:: BayesianClassifierImageFilter; VectorImage

Definition at line 76 of file itkBayesianClassifierInitializationImageFilter.h.