#include <itkBayesianClassifierImageFilter.h>

Inheritance diagram for itk::BayesianClassifierImageFilter< TInputVectorImage, TLabelsType, TPosteriorsPrecisionType, TPriorsPrecisionType >:

Collaboration diagram for itk::BayesianClassifierImageFilter< TInputVectorImage, TLabelsType, TPosteriorsPrecisionType, TPriorsPrecisionType >:

List of all members.

Public Types
typedef SmartPointer< const Self >	ConstPointer
typedef Superclass::DataObjectPointer	DataObjectPointer
typedef ProcessObject::DataObjectPointerArraySizeType	DataObjectPointerArraySizeType
typedef DecisionRuleType::Pointer	DecisionRulePointer
typedef Statistics::MaximumDecisionRule	DecisionRuleType
typedef itk::Image < TPosteriorsPrecisionType, itkGetStaticConstMacro(Dimension) >	ExtractedComponentImageType
typedef InputImageType::RegionType	ImageRegionType
typedef ImageRegionConstIterator < InputImageType >	InputImageIteratorType
typedef InputImageType::ConstPointer	InputImagePointer
typedef Superclass::InputImageType	InputImageType
typedef InputImageType::PixelType	InputPixelType
typedef ImageRegionConstIterator < MembershipImageType >	MembershipImageIteratorType
typedef MembershipImageType::Pointer	MembershipImagePointer
typedef TInputVectorImage	MembershipImageType
typedef MembershipImageType::PixelType	MembershipPixelType
typedef ImageRegionIterator < OutputImageType >	OutputImageIteratorType
typedef OutputImageType::Pointer	OutputImagePointer
typedef Image< TLabelsType, itkGetStaticConstMacro(Dimension) >	OutputImageType
typedef OutputImageType::PixelType	OutputPixelType
typedef SmartPointer< Self >	Pointer
typedef ImageRegionIterator < PosteriorsImageType >	PosteriorsImageIteratorType
typedef PosteriorsImageType::Pointer	PosteriorsImagePointer
typedef VectorImage < TPosteriorsPrecisionType, itkGetStaticConstMacro(Dimension) >	PosteriorsImageType
typedef PosteriorsImageType::PixelType	PosteriorsPixelType
typedef ImageRegionConstIterator < PriorsImageType >	PriorsImageIteratorType
typedef PriorsImageType::Pointer	PriorsImagePointer
typedef VectorImage < TPriorsPrecisionType, itkGetStaticConstMacro(Dimension) >	PriorsImageType
typedef PriorsImageType::PixelType	PriorsPixelType
typedef BayesianClassifierImageFilter	Self
typedef SmoothingFilterType::Pointer	SmoothingFilterPointer
typedef ImageToImageFilter < ExtractedComponentImageType, ExtractedComponentImageType >	SmoothingFilterType
typedef ImageToImageFilter < TInputVectorImage, Image < TLabelsType,::itk::GetImageDimension < TInputVectorImage > ::ImageDimension > >	Superclass
Public Member Functions
virtual ::itk::LightObject::Pointer	CreateAnother (void) const
virtual const char *	GetNameOfClass () const
virtual SmoothingFilterPointer	GetSmoothingFilter () const
virtual DataObjectPointer	MakeOutput (DataObjectPointerArraySizeType idx)
virtual void	SetPriors (const PriorsImageType *)
void	SetSmoothingFilter (SmoothingFilterType *)
	typedef (Concept::Convertible< unsigned int, TLabelsType >) UnsignedIntConvertibleToLabelsCheck
	typedef (Concept::AdditiveOperators< TPosteriorsPrecisionType >) PosteriorsAdditiveOperatorsCheck
	typedef (Concept::Convertible< int, TPosteriorsPrecisionType >) IntConvertibleToPosteriorsCheck
	typedef (Concept::HasNumericTraits< typename InputPixelType::ValueType >) InputHasNumericTraitsCheck
	typedef (Concept::HasNumericTraits< TPosteriorsPrecisionType >) PosteriorsHasNumericTraitsCheck
	typedef (Concept::HasNumericTraits< TPriorsPrecisionType >) PriorsHasNumericTraitsCheck
	typedef (Concept::MultiplyOperator< typename InputPixelType::ValueType, PriorsPixelType, PosteriorsPixelType >) InputPriorsPosteriorsMultiplyOperatorCheck

virtual void	SetNumberOfSmoothingIterations (unsigned int _arg)
virtual unsigned int	GetNumberOfSmoothingIterations () const
Static Public Member Functions
static Pointer	New ()
Static Public Attributes
static const unsigned int	Dimension = ::itk::GetImageDimension< InputImageType >::ImageDimension
Protected Member Functions
	BayesianClassifierImageFilter ()
virtual void	ClassifyBasedOnPosteriors ()
virtual void	ComputeBayesRule ()
virtual void	GenerateData ()
virtual void	GenerateOutputInformation (void)
PosteriorsImageType *	GetPosteriorImage ()
virtual void	NormalizeAndSmoothPosteriors ()
void	PrintSelf (std::ostream &os, Indent indent) const
virtual	~BayesianClassifierImageFilter ()
Private Member Functions
	BayesianClassifierImageFilter (const Self &)
void	operator= (const Self &)
Private Attributes
unsigned int	m_NumberOfSmoothingIterations
SmoothingFilterPointer	m_SmoothingFilter
bool	m_UserProvidedPriors
bool	m_UserProvidedSmoothingFilter

Detailed Description

template<class TInputVectorImage, class TLabelsType = unsigned char, class TPosteriorsPrecisionType = double, class TPriorsPrecisionType = double>
class itk::BayesianClassifierImageFilter< TInputVectorImage, TLabelsType, TPosteriorsPrecisionType, TPriorsPrecisionType >

Performs Bayesian Classification on an image.

Inputs and Outputs: The input to this filter is an itk::VectorImage that represents pixel memberships to 'n' classes. This image is conveniently generated by the BayesianClassifierInitializationImageFilter. You may use that filter to generate the membership images or specify your own.

: The output of the filter is a label map (an image of unsigned char's is the default.) with pixel values indicating the classes they correspond to. Pixels with intensity 0 belong to the 0th class, 1 belong to the 1st class etc.... The classification is done by applying a Maximum decision rule to the posterior image.

Parameters: The filter optionally allows you to specify a prior image as well. The prior image, if specified must be a VectorImage with as many components as the number of classes. The posterior image is then generated by multiplying the prior image with the membership image. If the prior image is not specified, the posterior image is the same as the membership image. Another way to look at it is that the priors default to having a uniform distribution over the number of classes. Posterior membership of a pixel = Prior * Membership

: The filter optionally accepts a smoothing filter and number of iterations associated with the smoothing filter. The philosophy is that the filter allows you to iteratively smooth the posteriors prior to applying the decision rule. It is hoped that this would yield a better classification. The user will need to plug in his own smoothing filter with all the parameters set.

Template parameters: InputVectorImage, datatype of the output labelmap, precision of the posterior image, precision of the prior image.

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:: VectorImage; BayesianClassifierInitializationImageFilter

Definition at line 81 of file itkBayesianClassifierImageFilter.h.