#include <itkWatershedRelabeler.h>

Inheritance diagram for itk::watershed::Relabeler< TScalarType, TImageDimension >:

Collaboration diagram for itk::watershed::Relabeler< TScalarType, TImageDimension >:

Public Types
typedef DataObject::Pointer	DataObjectPointer
typedef ProcessObject::DataObjectPointerArraySizeType	DataObjectPointerArraySizeType
typedef Image< IdentifierType, TImageDimension >	ImageType
typedef TScalarType	ScalarType
typedef Segmenter< Image < ScalarType, TImageDimension > >	SegmenterType
typedef SegmentTree< ScalarType >	SegmentTreeType
Public Member Functions
void	GenerateData ()
ImageType *	GetInputImage (void)
SegmentTreeType *	GetInputSegmentTree (void)
ImageType *	GetOutputImage (void)
void	GraftNthOutput (unsigned int idx, ImageType *graft)
void	GraftOutput (ImageType *graft)
virtual DataObjectPointer	MakeOutput (DataObjectPointerArraySizeType idx)
void	SetInputImage (ImageType *img)
void	SetInputSegmentTree (SegmentTreeType *et)
void	SetOutputImage (ImageType *img)

virtual void	SetFloodLevel (double _arg)
virtual double	GetFloodLevel () const
Static Public Attributes
static const unsigned int	ImageDimension = TImageDimension
Protected Member Functions
void	GenerateInputRequestedRegion ()
void	GenerateOutputRequestedRegion (DataObject *output)
void	operator= (const Self &)
void	PrintSelf (std::ostream &os, Indent indent) const
	Relabeler ()
	Relabeler (const Self &)
virtual	~Relabeler ()
Protected Attributes
double	m_FloodLevel
typedef Relabeler	Self
typedef ProcessObject	Superclass
typedef SmartPointer< Self >	Pointer
typedef SmartPointer< const Self >	ConstPointer
static Pointer	New ()
virtual ::itk::LightObject::Pointer	CreateAnother (void) const
virtual const char *	GetNameOfClass () const

Detailed Description

template<class TScalarType, unsigned int TImageDimension>
class itk::watershed::Relabeler< TScalarType, TImageDimension >

This filter implements the final step in the watershed segmentation algorithm. It is responsible for relabeling a segmented image according to a specified saliency level (flood level) in a merge tree. (See itk::WatershedImageFilter for information on terminology used in this documentation.)

Inputs: There are two inputs to this filter. The first input is a labeled image of unsigned long integers, such as is produced by itk::watershed::Segmenter. The second input is an itk::watershed::SegmentTree, which is the merge tree data structure produced by the itk::watershed::SegmentTreeGenerator filter. The merge tree represents the hierarchy of merges among adjacent segments in the initial segmentation image.

Output: The output of this filter is a relabeled image of unsigned long integers of dimension and size matching the input.

Parameters: There is a single parameter FloodLevel for this filter. FloodLevel is given in percentage points (0.0 - 1.0) of the maximum saliency found in the merge tree. A FloodLevel of 0.0 will produce an output in which no segments are relabeled (merged). A FloodLevel of 1.0 will produce an output in which all the entries in the merge tree are used to relabel the image. FloodLevel controls which level in the segmentation hierarchy to produce on the output.

See also:: itk::WatershedImageFilter; itk::EquivalencyTable; itk::watershed::SegmentTree

Definition at line 64 of file itkWatershedRelabeler.h.