This filter performs pixelwise voting among an arbitrary number of input images, where each of them represents a segmentation of the same scene (i.e., image). More...

#include <itkLabelVotingImageFilter.h>

Inheritance diagram for itk::LabelVotingImageFilter< TInputImage, TOutputImage >:

Collaboration diagram for itk::LabelVotingImageFilter< TInputImage, TOutputImage >:

List of all members.

Public Types
typedef SmartPointer< const Self >	ConstPointer
typedef InputImageType::ConstPointer	InputImagePointer
typedef TInputImage	InputImageType
typedef TInputImage::PixelType	InputPixelType
typedef OutputImageType::Pointer	OutputImagePointer
typedef Superclass::OutputImageRegionType	OutputImageRegionType
typedef TOutputImage	OutputImageType
typedef TOutputImage::PixelType	OutputPixelType
typedef SmartPointer< Self >	Pointer
typedef LabelVotingImageFilter	Self
typedef ImageToImageFilter < TInputImage, TOutputImage >	Superclass
Public Member Functions
virtual ::itk::LightObject::Pointer	CreateAnother (void) const
OutputPixelType	GetLabelForUndecidedPixels () const
virtual const char *	GetNameOfClass () const
	typedef (Concept::AdditiveOperators< InputPixelType, int >) InputPlusIntCheck
	typedef (Concept::Convertible< int, OutputPixelType >) IntConvertibleToOutputPixelType
	typedef (Concept::Convertible< InputPixelType, unsigned int >) InputConvertibleToUnsignedIntCheck
	typedef (Concept::SameDimension< InputImageDimension, ImageDimension >) SameDimensionCheck
	typedef (Concept::Convertible< int, InputPixelType >) IntConvertibleToInputCheck
	typedef (Concept::Convertible< InputPixelType, OutputPixelType >) InputConvertibleToOutputCheck
	typedef (Concept::OStreamWritable< OutputPixelType >) OutputOStreamWritableCheck
	typedef (Concept::IncrementDecrementOperators< InputPixelType >) InputIncrementDecrementOperatorsCheck

void	SetLabelForUndecidedPixels (const OutputPixelType l)

void	UnsetLabelForUndecidedPixels ()
Static Public Member Functions
static Pointer	New ()
Static Public Attributes

static const unsigned int	InputImageDimension = TInputImage::ImageDimension
static const unsigned int	ImageDimension = TOutputImage::ImageDimension
Protected Member Functions
void	BeforeThreadedGenerateData ()
InputPixelType	ComputeMaximumInputValue ()
void	PrintSelf (std::ostream &, Indent) const
void	ThreadedGenerateData (const OutputImageRegionType &outputRegionForThread, ThreadIdType threadId)

	LabelVotingImageFilter ()
virtual	~LabelVotingImageFilter ()
Private Member Functions
	LabelVotingImageFilter (const Self &)
void	operator= (const Self &)
Private Attributes
bool	m_HasLabelForUndecidedPixels
OutputPixelType	m_LabelForUndecidedPixels
InputPixelType	m_TotalLabelCount

Detailed Description

template<typename TInputImage, typename TOutputImage = TInputImage>
class itk::LabelVotingImageFilter< TInputImage, TOutputImage >

This filter performs pixelwise voting among an arbitrary number of input images, where each of them represents a segmentation of the same scene (i.e., image).

Label voting is a simple method of classifier combination applied to image segmentation. Typically, the accuracy of the combined segmentation exceeds the accuracy of any of the input segmentations. Voting is therefore commonly used as a way of boosting segmentation performance.

The use of label voting for combination of multiple segmentations is described in

T. Rohlfing and C. R. Maurer, Jr., "Multi-classifier framework for atlas-based image segmentation," Pattern Recognition Letters, 2005.

INPUTS: All input volumes to this filter must be segmentations of an image, that is, they must have discrete pixel values where each value represents a different segmented object.

Input volumes must all contain the same size RequestedRegions. Not all input images must contain all possible labels, but all label values must have the same meaning in all images.

OUTPUTS: The voting filter produces a single output volume. Each output pixel contains the label that occured most often among the labels assigned to this pixel in all the input volumes, that is, the label that received the maximum number of "votes" from the input pixels.. If the maximum number of votes is not unique, i.e., if more than one label have a maximum number of votes, an "undecided" label is assigned to that output pixel.

By default, the label used for undecided pixels is the maximum label value used in the input images plus one. Since it is possible for an image with 8 bit pixel values to use all 256 possible label values, it is permissible to combine 8 bit (i.e., byte) images into a 16 bit (i.e., short) output image.

PARAMETERS: The label used for "undecided" labels can be set using SetLabelForUndecidedPixels. This functionality can be unset by calling UnsetLabelForUndecidedPixels.

Author:: Torsten Rohlfing, SRI International, Neuroscience Program

Definition at line 75 of file itkLabelVotingImageFilter.h.