itk::Statistics::KdTreeGenerator< TSample > Class Template Reference

This class generates a KdTree object without centroid information. More...

#include <itkKdTreeGenerator.h>

Inheritance diagram for itk::Statistics::KdTreeGenerator< TSample >:

[legend]Collaboration diagram for itk::Statistics::KdTreeGenerator< TSample >:

[legend]List of all members.

Public Types
typedef KdTreeGenerator	Self
typedef Object	Superclass
typedef SmartPointer< Self >	Pointer
typedef SmartPointer< const Self >	ConstPointer
typedef TSample::MeasurementVectorType	MeasurementVectorType
typedef TSample::MeasurementType	MeasurementType
typedef unsigned int	MeasurementVectorSizeType
typedef KdTree< TSample >	KdTreeType
typedef KdTreeType	OutputType
typedef KdTreeType::Pointer	OutputPointer
typedef KdTreeType::KdTreeNodeType	KdTreeNodeType
typedef Subsample< TSample >	SubsampleType
typedef SubsampleType::Pointer	SubsamplePointer
Public Member Functions
virtual const char *	GetNameOfClass () const
void	SetSample (TSample *sample)
void	SetBucketSize (int size)
OutputPointer	GetOutput ()
void	Update ()
void	GenerateData ()
virtual unsigned int	GetMeasurementVectorSize () const
Static Public Member Functions
Pointer	New ()
Public Attributes
unsigned int	TotalInstance
Protected Member Functions
	KdTreeGenerator ()
virtual	~KdTreeGenerator ()
void	PrintSelf (std::ostream &os, Indent indent) const
SubsamplePointer	GetSubsample ()
virtual KdTreeNodeType *	GenerateNonterminalNode (int beginIndex, int endIndex, MeasurementVectorType &lowerBound, MeasurementVectorType &upperBound, int level)
KdTreeNodeType *	GenerateTreeLoop (int beginIndex, int endIndex, MeasurementVectorType &lowerBound, MeasurementVectorType &upperBound, int level)

---

Detailed Description

template<class TSample>
class itk::Statistics::KdTreeGenerator< TSample >

This class generates a KdTree object without centroid information.

The KdTree object stores measurment vectors in a k-d tree structure that is a binary tree. The partition value is the median value of one of the k dimension (partition dimension). The partition dimension is determined by the spread of measurement values in each dimension. The partition dimension is the dimension has the widest spread. Our implementation of k-d tree doesn't have any construction or insertion logic. Users should use this class or the WeightedCentroidKdTreeGenerator class.

The number of the measurement vectors in a terminal node is set by the SetBucketSize method. If we use too small number for this, it might cause computational overhead to calculate bound conditions. However, too large number will cause more distance calculation between the measurement vectors in a terminal node and the query point.

To run this generator, users should provides the bucket size (SetBucketSize method) and the input sample (SetSample method). The Update method will run this generator. To get the resulting KdTree object, call the GetOutput method.

Recent API changes: The static const macro to get the length of a measurement vector, 'MeasurementVectorSize' has been removed to allow the length of a measurement vector to be specified at run time. It is now obtained from the sample set as input. You may query this length using the function GetMeasurementVectorSize().

See also:

KdTree, KdTreeNode, KdTreeNonterminalNode, KdTreeTerminalNode, WeightedCentroidKdTreeGenerator

Definition at line 69 of file itkKdTreeGenerator.h.

---

Member Typedef Documentation

template<class TSample> typedef SmartPointer<const Self> itk::Statistics::KdTreeGenerator< TSample >::ConstPointer

Reimplemented from itk::Object. Reimplemented in itk::Statistics::WeightedCentroidKdTreeGenerator< TSample >. Definition at line 76 of file itkKdTreeGenerator.h.

template<class TSample> typedef KdTreeType::KdTreeNodeType itk::Statistics::KdTreeGenerator< TSample >::KdTreeNodeType

Typedef for the k-d tree node type Reimplemented in itk::Statistics::WeightedCentroidKdTreeGenerator< TSample >. Definition at line 101 of file itkKdTreeGenerator.h.

template<class TSample> typedef KdTree< TSample > itk::Statistics::KdTreeGenerator< TSample >::KdTreeType

Typedef for the k-d tree Reimplemented in itk::Statistics::WeightedCentroidKdTreeGenerator< TSample >. Definition at line 92 of file itkKdTreeGenerator.h.

template<class TSample> typedef TSample::MeasurementType itk::Statistics::KdTreeGenerator< TSample >::MeasurementType

Reimplemented in itk::Statistics::WeightedCentroidKdTreeGenerator< TSample >. Definition at line 86 of file itkKdTreeGenerator.h.

template<class TSample> typedef unsigned int itk::Statistics::KdTreeGenerator< TSample >::MeasurementVectorSizeType

Typedef for the length of each measurement vector Definition at line 89 of file itkKdTreeGenerator.h.

template<class TSample> typedef TSample::MeasurementVectorType itk::Statistics::KdTreeGenerator< TSample >::MeasurementVectorType

typedef alias for the source data container Reimplemented in itk::Statistics::WeightedCentroidKdTreeGenerator< TSample >. Definition at line 85 of file itkKdTreeGenerator.h.

template<class TSample> typedef KdTreeType::Pointer itk::Statistics::KdTreeGenerator< TSample >::OutputPointer

Typedef for the smart pointer to the k-d tree Definition at line 98 of file itkKdTreeGenerator.h. Referenced by itk::Statistics::KdTreeGenerator< TSample >::GetOutput().

template<class TSample> typedef KdTreeType itk::Statistics::KdTreeGenerator< TSample >::OutputType

Type alias for the k-d tree type Definition at line 95 of file itkKdTreeGenerator.h.

template<class TSample> typedef SmartPointer<Self> itk::Statistics::KdTreeGenerator< TSample >::Pointer

Reimplemented from itk::Object. Reimplemented in itk::Statistics::WeightedCentroidKdTreeGenerator< TSample >. Definition at line 75 of file itkKdTreeGenerator.h.

template<class TSample> typedef KdTreeGenerator itk::Statistics::KdTreeGenerator< TSample >::Self

Standard class typedefs Reimplemented from itk::Object. Reimplemented in itk::Statistics::WeightedCentroidKdTreeGenerator< TSample >. Definition at line 73 of file itkKdTreeGenerator.h.

template<class TSample> typedef SubsampleType::Pointer itk::Statistics::KdTreeGenerator< TSample >::SubsamplePointer

Typedef for the smart pointer to the Subsample Reimplemented in itk::Statistics::WeightedCentroidKdTreeGenerator< TSample >. Definition at line 107 of file itkKdTreeGenerator.h. Referenced by itk::Statistics::KdTreeGenerator< TSample >::GetSubsample().

template<class TSample> typedef Subsample< TSample > itk::Statistics::KdTreeGenerator< TSample >::SubsampleType

Typedef for the internal Subsample Reimplemented in itk::Statistics::WeightedCentroidKdTreeGenerator< TSample >. Definition at line 104 of file itkKdTreeGenerator.h.

template<class TSample> typedef Object itk::Statistics::KdTreeGenerator< TSample >::Superclass

Reimplemented from itk::Object. Reimplemented in itk::Statistics::WeightedCentroidKdTreeGenerator< TSample >. Definition at line 74 of file itkKdTreeGenerator.h.

---

Constructor & Destructor Documentation

template<class TSample> itk::Statistics::KdTreeGenerator< TSample >::KdTreeGenerator (   )  [protected]

Constructor

template<class TSample> virtual itk::Statistics::KdTreeGenerator< TSample >::~KdTreeGenerator (   )  [inline, protected, virtual]

Destructor Definition at line 139 of file itkKdTreeGenerator.h.

---

Member Function Documentation

template<class TSample> void itk::Statistics::KdTreeGenerator< TSample >::GenerateData (   )

Runs this k-d tree construction algorithm.

template<class TSample> virtual KdTreeNodeType* itk::Statistics::KdTreeGenerator< TSample >::GenerateNonterminalNode (  int  beginIndex, int  endIndex, MeasurementVectorType &  lowerBound, MeasurementVectorType &  upperBound, int  level )  [protected, virtual]

Nonterminal node generation routine Reimplemented in itk::Statistics::WeightedCentroidKdTreeGenerator< TSample >.

template<class TSample> KdTreeNodeType* itk::Statistics::KdTreeGenerator< TSample >::GenerateTreeLoop (  int  beginIndex, int  endIndex, MeasurementVectorType &  lowerBound, MeasurementVectorType &  upperBound, int  level )  [protected]

Tree generation loop

template<class TSample> virtual unsigned int itk::Statistics::KdTreeGenerator< TSample >::GetMeasurementVectorSize (   )  const [virtual]

Get macro to get the length of the measurement vectors that are being held in the 'sample' that is passed to this class

template<class TSample> virtual const char* itk::Statistics::KdTreeGenerator< TSample >::GetNameOfClass (   )  const [virtual]

Run-time type information (and related methods) Reimplemented from itk::Object. Reimplemented in itk::Statistics::WeightedCentroidKdTreeGenerator< TSample >.

template<class TSample> OutputPointer itk::Statistics::KdTreeGenerator< TSample >::GetOutput (  void   )  [inline]

Returns the pointer to the generated k-d tree. Definition at line 117 of file itkKdTreeGenerator.h. References itk::Statistics::KdTreeGenerator< TSample >::OutputPointer.

template<class TSample> SubsamplePointer itk::Statistics::KdTreeGenerator< TSample >::GetSubsample (   )  [inline, protected]

Returns the smart pointer to the internal Subsample object. Definition at line 144 of file itkKdTreeGenerator.h. References itk::Statistics::KdTreeGenerator< TSample >::SubsamplePointer.

template<class TSample> Pointer itk::Statistics::KdTreeGenerator< TSample >::New (   )  [static]

Method for creation through the object factory. Reimplemented from itk::Object. Reimplemented in itk::Statistics::WeightedCentroidKdTreeGenerator< TSample >.

template<class TSample> void itk::Statistics::KdTreeGenerator< TSample >::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::Object. Reimplemented in itk::Statistics::WeightedCentroidKdTreeGenerator< TSample >.

template<class TSample> void itk::Statistics::KdTreeGenerator< TSample >::SetBucketSize (  int  size  )

Sets the number of measurement vectors that can be stored in a terminal node.

template<class TSample> void itk::Statistics::KdTreeGenerator< TSample >::SetSample (  TSample *  sample  )

Sets the input sample that provides the measurement vectors.

template<class TSample> void itk::Statistics::KdTreeGenerator< TSample >::Update (  void   )  [inline]

Runs this k-d tree construction algorithm. Definition at line 121 of file itkKdTreeGenerator.h.

---

Member Data Documentation

template<class TSample> unsigned int itk::Statistics::KdTreeGenerator< TSample >::TotalInstance

The number of measurement vectors in an object of this class. Definition at line 128 of file itkKdTreeGenerator.h.

---

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

• itkKdTreeGenerator.h

---