#include <itkWatershedSegmentTreeGenerator.h>

Inheritance diagram for itk::watershed::SegmentTreeGenerator< TScalarType >:

Collaboration diagram for itk::watershed::SegmentTreeGenerator< TScalarType >:

Public Types
typedef DataObject::Pointer	DataObjectPointer
typedef ProcessObject::DataObjectPointerArraySizeType	DataObjectPointerArraySizeType
typedef EquivalencyTable	EquivalencyTableType
typedef OneWayEquivalencyTable	OneWayEquivalencyTableType
typedef OneWayEquivalencyTableType::Pointer	OneWayEquivalencyTableTypePointer
typedef TScalarType	ScalarType
typedef SegmentTable< ScalarType >	SegmentTableType
typedef SegmentTableType::Pointer	SegmentTableTypePointer
typedef SegmentTree< ScalarType >	SegmentTreeType
typedef SegmentTreeType::Pointer	SegmentTreeTypePointer
Public Member Functions
void	GenerateData ()
virtual double	GetFloodLevel () const
EquivalencyTableType *	GetInputEquivalencyTable ()
SegmentTableType *	GetInputSegmentTable ()
SegmentTreeType *	GetOutputSegmentTree ()
virtual DataObjectPointer	MakeOutput (DataObjectPointerArraySizeType idx)
void	SetFloodLevel (double)
void	SetInputEquivalencyTable (EquivalencyTableType *eq)
void	SetInputSegmentTable (SegmentTableType *st)

virtual void	SetMerge (bool _arg)
virtual bool	GetMerge () const

virtual void	SetHighestCalculatedFloodLevel (double _arg)
virtual double	GetHighestCalculatedFloodLevel () const

virtual void	SetConsumeInput (bool _arg)
virtual bool	GetConsumeInput () const
Static Public Member Functions
static void	MergeSegments (SegmentTableTypePointer, OneWayEquivalencyTableTypePointer, const IdentifierType, const IdentifierType)
static void	PruneMergeSegments (SegmentTableTypePointer, OneWayEquivalencyTableTypePointer, const IdentifierType, const IdentifierType, ScalarType)
Protected Member Functions
void	CompileMergeList (SegmentTableTypePointer, SegmentTreeTypePointer)
void	ExtractMergeHierarchy (SegmentTableTypePointer, SegmentTreeTypePointer)
void	GenerateInputRequestedRegion ()
void	GenerateOutputRequestedRegion (DataObject *output)
void	MergeEquivalencies ()
void	operator= (const Self &)
void	PrintSelf (std::ostream &os, Indent indent) const
	SegmentTreeGenerator ()
	SegmentTreeGenerator (const Self &)
virtual	~SegmentTreeGenerator ()
Private Types
typedef itksys::hash_map < IdentifierType, bool, itksys::hash< IdentifierType > >	HashMapType
Private Attributes
bool	m_ConsumeInput
double	m_FloodLevel
double	m_HighestCalculatedFloodLevel
bool	m_Merge
OneWayEquivalencyTableType::Pointer	m_MergedSegmentsTable
typedef SegmentTreeGenerator	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>
class itk::watershed::SegmentTreeGenerator< TScalarType >

This filter is a process object class that implements a step in the N-d watershed segmentation algorithm. It produces an ordered list (SegmentTree) of binary merges between segments at increasing saliency levels. This filter is used in conjunction with WatershedSegmenter and WatershedRelabeler to process an initial segmentation into a final relabeled volume. See itk::WatershedImageFilter for an overview of watershed segmentation.

Inputs: There are two inputs to this filter, the second is optional. (1) A table of segments (SegmentTable) derived from a labeled image. (2) Optionally, a table of predetermined equivalencies among segments (EquivalencyTable), necessary for streaming applications where segments may be joined across streamed chunk boundaries. The flag Merge must be set to true to enable this functionality.

Outputs: The output of this filter is a list of binary merges of segments at increasing saliency. This is the data structure itk::watershed::WatershedSegmentTree referred to as a ``merge tree'' in the itk::WatershedImageFilter documentation.

Parameters: There are two parameters to this filter described below.

: FloodLevel is specified as a percentage (0.0 - 1.0) of the maximum possible saliency value in the initial image from which the segment table was derived. A value of 0.0 calculates no merges. A value of 1.0 calculates all of the potential merges that can occur as the FloodLevel is increased to the maximum saliency value. Typically, there is no need to calculate merges past about 40% of the total depth. Because this is the most computationally intensive piece of the watershed segmentation algorithm, it is a good idea to tune this parameter as low as possible on larger volumes.

: Merge is a boolean flag indicating whether or not to pre-merge the segments marked as equivalent in the EquivalencyTable. This is only useful for streaming applications and is turned off by default. (TRUE == merge, FALSE == do not merge).

See also:: itk::WatershedImageFilter

Definition at line 78 of file itkWatershedSegmentTreeGenerator.h.

Member Typedef Documentation

template<class TScalarType>

typedef SmartPointer< const Self > itk::watershed::SegmentTreeGenerator< TScalarType >::ConstPointer

Standard itk smart pointer declarations

Reimplemented from itk::ProcessObject.

Definition at line 86 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

typedef DataObject::Pointer itk::watershed::SegmentTreeGenerator< TScalarType >::DataObjectPointer

Smart Pointer type to a DataObject.

Reimplemented from itk::ProcessObject.

Definition at line 97 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

typedef ProcessObject::DataObjectPointerArraySizeType itk::watershed::SegmentTreeGenerator< TScalarType >::DataObjectPointerArraySizeType

Standard itk::ProcessObject subclass method.

Reimplemented from itk::ProcessObject.

Definition at line 194 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

typedef EquivalencyTable itk::watershed::SegmentTreeGenerator< TScalarType >::EquivalencyTableType

Definition at line 95 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

typedef itksys::hash_map< IdentifierType, bool, itksys::hash< IdentifierType > > itk::watershed::SegmentTreeGenerator< TScalarType >::HashMapType [private]

Definition at line 226 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

typedef OneWayEquivalencyTable itk::watershed::SegmentTreeGenerator< TScalarType >::OneWayEquivalencyTableType

Definition at line 96 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

typedef OneWayEquivalencyTableType::Pointer itk::watershed::SegmentTreeGenerator< TScalarType >::OneWayEquivalencyTableTypePointer

Definition at line 101 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

typedef SmartPointer< Self > itk::watershed::SegmentTreeGenerator< TScalarType >::Pointer

Standard itk smart pointer declarations

Reimplemented from itk::ProcessObject.

Definition at line 85 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

typedef TScalarType itk::watershed::SegmentTreeGenerator< TScalarType >::ScalarType

Convenient type definitions

Definition at line 88 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

typedef SegmentTable< ScalarType > itk::watershed::SegmentTreeGenerator< TScalarType >::SegmentTableType

Definition at line 93 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

typedef SegmentTableType::Pointer itk::watershed::SegmentTreeGenerator< TScalarType >::SegmentTableTypePointer

Typedefs to avoid internal compiler error bug on Microsoft VC++

Definition at line 100 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

typedef SegmentTree< ScalarType > itk::watershed::SegmentTreeGenerator< TScalarType >::SegmentTreeType

Definition at line 94 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

typedef SegmentTreeType::Pointer itk::watershed::SegmentTreeGenerator< TScalarType >::SegmentTreeTypePointer

Definition at line 102 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

typedef SegmentTreeGenerator itk::watershed::SegmentTreeGenerator< TScalarType >::Self

Standard itk smart pointer declarations

Reimplemented from itk::ProcessObject.

Definition at line 83 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

typedef ProcessObject itk::watershed::SegmentTreeGenerator< TScalarType >::Superclass

Standard itk smart pointer declarations

Reimplemented from itk::ProcessObject.

Definition at line 84 of file itkWatershedSegmentTreeGenerator.h.

Constructor & Destructor Documentation

template<class TScalarType>

itk::watershed::SegmentTreeGenerator< TScalarType >::SegmentTreeGenerator ( ) [protected]

template<class TScalarType>

virtual itk::watershed::SegmentTreeGenerator< TScalarType >::~SegmentTreeGenerator ( ) [inline, protected, virtual]

Definition at line 200 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

itk::watershed::SegmentTreeGenerator< TScalarType >::SegmentTreeGenerator ( const Self & ) [inline, protected]

Definition at line 201 of file itkWatershedSegmentTreeGenerator.h.

Member Function Documentation

template<class TScalarType>

void itk::watershed::SegmentTreeGenerator< TScalarType >::CompileMergeList	(	SegmentTableTypePointer	,
		SegmentTreeTypePointer
	)		`[protected]`

Generates an initial list of all potentential merges in the segment table.

template<class TScalarType>

virtual::itk::LightObject::Pointer itk::watershed::SegmentTreeGenerator< TScalarType >::CreateAnother ( void ) const [virtual]

Standard itk smart pointer declarations

Reimplemented from itk::Object.

template<class TScalarType>

void itk::watershed::SegmentTreeGenerator< TScalarType >::ExtractMergeHierarchy	(	SegmentTableTypePointer	,
		SegmentTreeTypePointer
	)		`[protected]`

Compiles a list of all the actual segment merges up to the specified flood level, recomputing new potential merges as it goes.

template<class TScalarType>

void itk::watershed::SegmentTreeGenerator< TScalarType >::GenerateData ( ) [virtual]

Standard non-threaded itk pipeline method

Reimplemented from itk::ProcessObject.

template<class TScalarType>

void itk::watershed::SegmentTreeGenerator< TScalarType >::GenerateInputRequestedRegion ( ) [protected, virtual]

What is the input requested region that is required to produce the output requested region? By default, the largest possible region is always required but this is overridden in many subclasses. For instance, for an image processing filter where an output pixel is a simple function of an input pixel, the input requested region will be set to the output requested region. For an image processing filter where an output pixel is a function of the pixels in a neighborhood of an input pixel, then the input requested region will need to be larger than the output requested region (to avoid introducing artificial boundary conditions). This function should never request an input region that is outside the the input largest possible region (i.e. implementations of this method should crop the input requested region at the boundaries of the input largest possible region).

Reimplemented from itk::ProcessObject.

template<class TScalarType>

void itk::watershed::SegmentTreeGenerator< TScalarType >::GenerateOutputRequestedRegion ( DataObject * output ) [protected, virtual]

Methods required by the itk pipeline

Reimplemented from itk::ProcessObject.

template<class TScalarType>

virtual bool itk::watershed::SegmentTreeGenerator< TScalarType >::GetConsumeInput ( ) const [virtual]

Get/Set a flag that prevents the filter from copying its input segment table before executing. This can be enabled to conserve memory, especially in streaming applications where memory is a concern. If enabled, the input to this filter must always be re-executed on updates. Default is false.

template<class TScalarType>

virtual double itk::watershed::SegmentTreeGenerator< TScalarType >::GetFloodLevel ( ) const [virtual]

template<class TScalarType>

virtual double itk::watershed::SegmentTreeGenerator< TScalarType >::GetHighestCalculatedFloodLevel ( ) const [virtual]

Get/Set HighestCalculatedFloodLevel. HighestCalculatedFloodLevel keeps track of the highest level this filter has computed. It is used to prevent unneccessary re-execution of the filter.

template<class TScalarType>

EquivalencyTableType* itk::watershed::SegmentTreeGenerator< TScalarType >::GetInputEquivalencyTable ( ) [inline]

Definition at line 129 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

SegmentTableType* itk::watershed::SegmentTreeGenerator< TScalarType >::GetInputSegmentTable ( ) [inline]

Get/Set the input table of segments to process

Definition at line 105 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

virtual bool itk::watershed::SegmentTreeGenerator< TScalarType >::GetMerge ( ) const [virtual]

Get/Set a boolean flag indicating whether or not to pre-merge the segments marked as equivalent in the EquivalencyTable. This is only useful for streaming applications and is turned off by default. (TRUE == merge, FALSE == do not merge).

template<class TScalarType>

virtual const char* itk::watershed::SegmentTreeGenerator< TScalarType >::GetNameOfClass ( ) const [virtual]

Standard itk smart pointer declarations

Reimplemented from itk::ProcessObject.

template<class TScalarType>

SegmentTreeType* itk::watershed::SegmentTreeGenerator< TScalarType >::GetOutputSegmentTree ( ) [inline]

Get/Set the output data

Definition at line 136 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

virtual DataObjectPointer itk::watershed::SegmentTreeGenerator< TScalarType >::MakeOutput ( DataObjectPointerArraySizeType idx ) [virtual]

Make a DataObject of the correct type to used as the specified output. Every ProcessObject subclass must be able to create a DataObject that can be used as a specified output. This method is automatically called when DataObject::DisconnectPipeline() is called. DataObject::DisconnectPipeline, disconnects a data object from being an output of its current source. When the data object is disconnected, the ProcessObject needs to construct a replacement output data object so that the ProcessObject is in a valid state. So DataObject::DisconnectPipeline eventually calls ProcessObject::MakeOutput. Note that MakeOutput always returns a itkSmartPointer to a DataObject. ImageSource and MeshSource override this method to create the correct type of image and mesh respectively. If a filter has multiple outputs of different types, then that filter must provide an implementation of MakeOutput().

Reimplemented from itk::ProcessObject.

template<class TScalarType>

void itk::watershed::SegmentTreeGenerator< TScalarType >::MergeEquivalencies ( ) [protected]

template<class TScalarType>

static void itk::watershed::SegmentTreeGenerator< TScalarType >::MergeSegments	(	SegmentTableTypePointer	,
		OneWayEquivalencyTableTypePointer	,
		const IdentifierType	,
		const IdentifierType
	)		`[static]`

Performs a merge of two segments in a SegmentTable according to criteria specific to this algorithm.

template<class TScalarType>

static Pointer itk::watershed::SegmentTreeGenerator< TScalarType >::New ( ) [static]

Standard itk smart pointer declarations

Reimplemented from itk::Object.

template<class TScalarType>

void itk::watershed::SegmentTreeGenerator< TScalarType >::operator= ( const Self & ) [inline, protected]

Time when GenerateOutputInformation was last called.

Reimplemented from itk::ProcessObject.

Definition at line 202 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

void itk::watershed::SegmentTreeGenerator< TScalarType >::PrintSelf	(	std::ostream &	os,
		Indent	indent
	)		const `[protected, virtual]`

Methods invoked by Print() to print information about the object including superclasses. Typically not called by the user (use Print() instead) but used in the hierarchical print process to combine the output of several classes.

Reimplemented from itk::ProcessObject.

template<class TScalarType>

static void itk::watershed::SegmentTreeGenerator< TScalarType >::PruneMergeSegments	(	SegmentTableTypePointer	,
		OneWayEquivalencyTableTypePointer	,
		const IdentifierType	,
		const IdentifierType	,
		ScalarType
	)		`[static]`

This method should not be used. It will be removed in future versions of this filter.

template<class TScalarType>

virtual void itk::watershed::SegmentTreeGenerator< TScalarType >::SetConsumeInput ( bool _arg ) [virtual]

Get/Set a flag that prevents the filter from copying its input segment table before executing. This can be enabled to conserve memory, especially in streaming applications where memory is a concern. If enabled, the input to this filter must always be re-executed on updates. Default is false.

template<class TScalarType>

void itk::watershed::SegmentTreeGenerator< TScalarType >::SetFloodLevel ( double )

Get/Set FloodLevel. FloodLevel is specified as a percentage (0.0 - 1.0) of the maximum possible saliency value in the initial image from which the segment table was derived. A value of 0.0 calculates no merges. A value of 1.0 calculates all of the potential merges that can occur as the FloodLevel is increased to the maximum saliency value.

template<class TScalarType>

virtual void itk::watershed::SegmentTreeGenerator< TScalarType >::SetHighestCalculatedFloodLevel ( double _arg ) [virtual]

Get/Set HighestCalculatedFloodLevel. HighestCalculatedFloodLevel keeps track of the highest level this filter has computed. It is used to prevent unneccessary re-execution of the filter.

template<class TScalarType>

void itk::watershed::SegmentTreeGenerator< TScalarType >::SetInputEquivalencyTable ( EquivalencyTableType * eq ) [inline]

Get/Set input table of equivalencies to pre-merge before running the tree generator algorithm. Only useful for streaming applications

Definition at line 124 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

void itk::watershed::SegmentTreeGenerator< TScalarType >::SetInputSegmentTable ( SegmentTableType * st ) [inline]

Definition at line 110 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

virtual void itk::watershed::SegmentTreeGenerator< TScalarType >::SetMerge ( bool _arg ) [virtual]

Get/Set a boolean flag indicating whether or not to pre-merge the segments marked as equivalent in the EquivalencyTable. This is only useful for streaming applications and is turned off by default. (TRUE == merge, FALSE == do not merge).

Member Data Documentation

template<class TScalarType>

bool itk::watershed::SegmentTreeGenerator< TScalarType >::m_ConsumeInput [private]

Definition at line 223 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

double itk::watershed::SegmentTreeGenerator< TScalarType >::m_FloodLevel [private]

Definition at line 222 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

double itk::watershed::SegmentTreeGenerator< TScalarType >::m_HighestCalculatedFloodLevel [private]

This value keeps track of the highest level this filter has been calculated. m_FloodLevel can be manipulated anywhere below this level without re-executing the filter, preventing unneccesary updates.

Definition at line 234 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

bool itk::watershed::SegmentTreeGenerator< TScalarType >::m_Merge [private]

Definition at line 221 of file itkWatershedSegmentTreeGenerator.h.

template<class TScalarType>

OneWayEquivalencyTableType::Pointer itk::watershed::SegmentTreeGenerator< TScalarType >::m_MergedSegmentsTable [private]

Definition at line 228 of file itkWatershedSegmentTreeGenerator.h.

The documentation for this class was generated from the following file: