#include <itkKdTreeBasedKmeansEstimator.h>

Inheritance diagram for itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >:

Collaboration diagram for itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >:

Classes
class	CandidateVector

Public Types
using	CentroidType = typename KdTreeNodeType::CentroidType

using	ConstPointer = SmartPointer< const Self >

using	DistanceToCentroidMembershipFunctionPointer = typename DistanceToCentroidMembershipFunctionType::Pointer

using	DistanceToCentroidMembershipFunctionType = DistanceToCentroidMembershipFunction< MeasurementVectorType >

using	InstanceIdentifier = typename TKdTree::InstanceIdentifier

using	InternalParametersType = std::vector< ParameterType >

using	KdTreeNodeType = typename TKdTree::KdTreeNodeType

using	MeasurementType = typename TKdTree::MeasurementType

using	MeasurementVectorSizeType = unsigned int

using	MeasurementVectorType = typename TKdTree::MeasurementVectorType

using	MembershipFunctionPointer = typename MembershipFunctionType::ConstPointer

using	MembershipFunctionType = MembershipFunctionBase< MeasurementVectorType >

using	MembershipFunctionVectorObjectPointer = typename MembershipFunctionVectorObjectType::Pointer

using	MembershipFunctionVectorObjectType = SimpleDataObjectDecorator< MembershipFunctionVectorType >

using	MembershipFunctionVectorType = std::vector< MembershipFunctionPointer >

using	ParametersType = Array< double >

using	ParameterType = Array< double >

using	Pointer = SmartPointer< Self >

using	SampleType = typename TKdTree::SampleType

using	Self = KdTreeBasedKmeansEstimator

using	Superclass = Object

Public Types inherited from itk::Object
using	ConstPointer = SmartPointer< const Self >

using	Pointer = SmartPointer< Self >

using	Self = Object

using	Superclass = LightObject

Public Types inherited from itk::LightObject
using	ConstPointer = SmartPointer< const Self >

using	Pointer = SmartPointer< Self >

using	Self = LightObject

Public Member Functions
virtual ::itk::LightObject::Pointer	CreateAnother () const

virtual const char *	GetNameOfClass () const

const MembershipFunctionVectorObjectType *	GetOutput () const

Public Member Functions inherited from itk::Object
unsigned long	AddObserver (const EventObject &event, Command *)

unsigned long	AddObserver (const EventObject &event, Command *) const

unsigned long	AddObserver (const EventObject &event, std::function< void(const EventObject &)> function) const

virtual void	DebugOff () const

virtual void	DebugOn () const

Command *	GetCommand (unsigned long tag)

bool	GetDebug () const

MetaDataDictionary &	GetMetaDataDictionary ()

const MetaDataDictionary &	GetMetaDataDictionary () const

virtual ModifiedTimeType	GetMTime () const

virtual const TimeStamp &	GetTimeStamp () const

bool	HasObserver (const EventObject &event) const

void	InvokeEvent (const EventObject &)

void	InvokeEvent (const EventObject &) const

virtual void	Modified () const

void	Register () const override

void	RemoveAllObservers ()

void	RemoveObserver (unsigned long tag)

void	SetDebug (bool debugFlag) const

void	SetReferenceCount (int) override

void	UnRegister () const noexcept override

void	SetMetaDataDictionary (const MetaDataDictionary &rhs)

void	SetMetaDataDictionary (MetaDataDictionary &&rrhs)

virtual void	SetObjectName (std::string _arg)

virtual const std::string &	GetObjectName () const

Public Member Functions inherited from itk::LightObject
Pointer	Clone () const

virtual void	Delete ()

virtual int	GetReferenceCount () const

void	Print (std::ostream &os, Indent indent=0) const

Static Public Member Functions
static Pointer	New ()

Static Public Member Functions inherited from itk::Object
static bool	GetGlobalWarningDisplay ()

static void	GlobalWarningDisplayOff ()

static void	GlobalWarningDisplayOn ()

static Pointer	New ()

static void	SetGlobalWarningDisplay (bool val)

Static Public Member Functions inherited from itk::LightObject
static void	BreakOnError ()

static Pointer	New ()

using	ClusterLabelsType = std::unordered_map< InstanceIdentifier, unsigned int >

int	m_CurrentIteration { 0 }

int	m_MaximumIteration { 100 }

double	m_CentroidPositionChanges { 0.0 }

double	m_CentroidPositionChangesThreshold { 0.0 }

TKdTree::Pointer	m_KdTree

EuclideanDistanceMetric< ParameterType >::Pointer	m_DistanceMetric

ParametersType	m_Parameters

CandidateVector	m_CandidateVector

ParameterType	m_TempVertex

bool	m_UseClusterLabels { false }

bool	m_GenerateClusterLabels { false }

ClusterLabelsType	m_ClusterLabels

MeasurementVectorSizeType	m_MeasurementVectorSize { 0 }

MembershipFunctionVectorObjectPointer	m_MembershipFunctionsObject

virtual void	SetParameters (ParametersType _arg)

virtual ParametersType	GetParameters () const

virtual void	SetMaximumIteration (int _arg)

virtual int	GetMaximumIteration () const

virtual void	SetCentroidPositionChangesThreshold (double _arg)

virtual double	GetCentroidPositionChangesThreshold () const

void	SetKdTree (TKdTree *tree)

const TKdTree *	GetKdTree () const

virtual MeasurementVectorSizeType	GetMeasurementVectorSize () const

virtual int	GetCurrentIteration () const

virtual double	GetCentroidPositionChanges () const

void	StartOptimization ()

virtual void	SetUseClusterLabels (bool _arg)

virtual bool	GetUseClusterLabels () const

	KdTreeBasedKmeansEstimator ()

	~KdTreeBasedKmeansEstimator () override=default

void	PrintSelf (std::ostream &os, Indent indent) const override

void	FillClusterLabels (KdTreeNodeType *node, int closestIndex)

double	GetSumOfSquaredPositionChanges (InternalParametersType &previous, InternalParametersType &current)

int	GetClosestCandidate (ParameterType &measurements, std::vector< int > &validIndexes)

bool	IsFarther (ParameterType &pointA, ParameterType &pointB, MeasurementVectorType &lowerBound, MeasurementVectorType &upperBound)

void	Filter (KdTreeNodeType *node, std::vector< int > validIndexes, MeasurementVectorType &lowerBound, MeasurementVectorType &upperBound)

void	CopyParameters (InternalParametersType &source, InternalParametersType &target)

void	CopyParameters (ParametersType &source, InternalParametersType &target)

void	CopyParameters (InternalParametersType &source, ParametersType &target)

void	GetPoint (ParameterType &point, MeasurementVectorType measurements)

void	PrintPoint (ParameterType &point)

Additional Inherited Members
Protected Member Functions inherited from itk::Object
	Object ()

	~Object () override

bool	PrintObservers (std::ostream &os, Indent indent) const

virtual void	SetTimeStamp (const TimeStamp &timeStamp)

Protected Member Functions inherited from itk::LightObject
virtual LightObject::Pointer	InternalClone () const

	LightObject ()

virtual void	PrintHeader (std::ostream &os, Indent indent) const

virtual void	PrintTrailer (std::ostream &os, Indent indent) const

virtual	~LightObject ()

Protected Attributes inherited from itk::LightObject
std::atomic< int >	m_ReferenceCount

Detailed Description

template<typename TKdTree>
class itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >

fast k-means algorithm implementation using k-d tree structure

It returns k mean vectors that are centroids of k-clusters using pre-generated k-d tree. k-d tree generation is done by the WeightedCentroidKdTreeGenerator. The tree construction needs to be done only once. The resulting k-d tree's non-terminal nodes that have their children nodes have vector sums of measurement vectors that belong to the nodes and the number of measurement vectors in addition to the typical node boundary information and pointers to children nodes. Instead of reassigning every measurement vector to the nearest cluster centroid and recalculating centroid, it maintain a set of cluster centroid candidates and using pruning algorithm that utilizes k-d tree, it updates the means of only relevant candidates at each iterations. It would be faster than traditional implementation of k-means algorithm. However, the k-d tree consumes a large amount of memory. The tree construction time and pruning algorithm's performance are important factors to the whole process's performance. If users want to use k-d tree for some purpose other than k-means estimation, they can use the KdTreeGenerator instead of the WeightedCentroidKdTreeGenerator. It will save the tree construction time and memory usage.

Note: There is a second implementation of k-means algorithm in ITK under the While the Kd tree based implementation is more time efficient, the GLA/LBG based algorithm is more memory efficient.

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 KdTree set as input. You may query this length using the function GetMeasurementVectorSize().

See also: ImageKmeansModelEstimator; WeightedCentroidKdTreeGenerator, KdTree

Examples: Examples/Statistics/KdTreeBasedKMeansClustering.cxx, and Examples/Statistics/ScalarImageKmeansModelEstimator.cxx.

Definition at line 74 of file itkKdTreeBasedKmeansEstimator.h.

Member Typedef Documentation

◆ CentroidType

template<typename TKdTree >

using itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::CentroidType = typename KdTreeNodeType::CentroidType

Definition at line 95 of file itkKdTreeBasedKmeansEstimator.h.

◆ ClusterLabelsType

template<typename TKdTree >

using itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::ClusterLabelsType = std::unordered_map<InstanceIdentifier, unsigned int>

current number of iteration

Definition at line 158 of file itkKdTreeBasedKmeansEstimator.h.

◆ ConstPointer

template<typename TKdTree >

using itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::ConstPointer = SmartPointer<const Self>

Definition at line 81 of file itkKdTreeBasedKmeansEstimator.h.

◆ DistanceToCentroidMembershipFunctionPointer

template<typename TKdTree >

using itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::DistanceToCentroidMembershipFunctionPointer = typename DistanceToCentroidMembershipFunctionType::Pointer

Definition at line 110 of file itkKdTreeBasedKmeansEstimator.h.

◆ DistanceToCentroidMembershipFunctionType

template<typename TKdTree >

using itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::DistanceToCentroidMembershipFunctionType = DistanceToCentroidMembershipFunction<MeasurementVectorType>

Typedef required to generate dataobject decorated output that can be plugged into SampleClassifierFilter

Definition at line 108 of file itkKdTreeBasedKmeansEstimator.h.

◆ InstanceIdentifier

template<typename TKdTree >

using itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::InstanceIdentifier = typename TKdTree::InstanceIdentifier

Definition at line 93 of file itkKdTreeBasedKmeansEstimator.h.

◆ InternalParametersType

template<typename TKdTree >

using itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::InternalParametersType = std::vector<ParameterType>

Definition at line 103 of file itkKdTreeBasedKmeansEstimator.h.

◆ KdTreeNodeType

template<typename TKdTree >

using itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::KdTreeNodeType = typename TKdTree::KdTreeNodeType

Types for the KdTree data structure

Definition at line 90 of file itkKdTreeBasedKmeansEstimator.h.

◆ MeasurementType

template<typename TKdTree >

using itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::MeasurementType = typename TKdTree::MeasurementType

Definition at line 91 of file itkKdTreeBasedKmeansEstimator.h.

◆ MeasurementVectorSizeType

template<typename TKdTree >

using itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::MeasurementVectorSizeType = unsigned int

Typedef for the length of a measurement vector

Definition at line 98 of file itkKdTreeBasedKmeansEstimator.h.

◆ MeasurementVectorType

template<typename TKdTree >

using itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::MeasurementVectorType = typename TKdTree::MeasurementVectorType

Definition at line 92 of file itkKdTreeBasedKmeansEstimator.h.

◆ MembershipFunctionPointer

template<typename TKdTree >

using itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::MembershipFunctionPointer = typename MembershipFunctionType::ConstPointer

Definition at line 113 of file itkKdTreeBasedKmeansEstimator.h.

◆ MembershipFunctionType

template<typename TKdTree >

using itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::MembershipFunctionType = MembershipFunctionBase<MeasurementVectorType>

Definition at line 112 of file itkKdTreeBasedKmeansEstimator.h.

◆ MembershipFunctionVectorObjectPointer

template<typename TKdTree >

using itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::MembershipFunctionVectorObjectPointer = typename MembershipFunctionVectorObjectType::Pointer

Definition at line 116 of file itkKdTreeBasedKmeansEstimator.h.

◆ MembershipFunctionVectorObjectType

template<typename TKdTree >

using itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::MembershipFunctionVectorObjectType = SimpleDataObjectDecorator<MembershipFunctionVectorType>

Definition at line 115 of file itkKdTreeBasedKmeansEstimator.h.

◆ MembershipFunctionVectorType

template<typename TKdTree >

using itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::MembershipFunctionVectorType = std::vector<MembershipFunctionPointer>

Definition at line 114 of file itkKdTreeBasedKmeansEstimator.h.

◆ ParametersType

template<typename TKdTree >

using itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::ParametersType = Array<double>

Definition at line 104 of file itkKdTreeBasedKmeansEstimator.h.

◆ ParameterType

template<typename TKdTree >

using itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::ParameterType = Array<double>

Parameters type. It defines a position in the optimization search space.

Definition at line 102 of file itkKdTreeBasedKmeansEstimator.h.

◆ Pointer

template<typename TKdTree >

using itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::Pointer = SmartPointer<Self>

Definition at line 80 of file itkKdTreeBasedKmeansEstimator.h.

◆ SampleType

template<typename TKdTree >

using itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::SampleType = typename TKdTree::SampleType

Definition at line 94 of file itkKdTreeBasedKmeansEstimator.h.

◆ Self

template<typename TKdTree >

using itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::Self = KdTreeBasedKmeansEstimator

Standard Self type alias.

Definition at line 78 of file itkKdTreeBasedKmeansEstimator.h.

◆ Superclass

template<typename TKdTree >

using itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::Superclass = Object

Definition at line 79 of file itkKdTreeBasedKmeansEstimator.h.

Constructor & Destructor Documentation

◆ KdTreeBasedKmeansEstimator()

template<typename TKdTree >

itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::KdTreeBasedKmeansEstimator ( )

protected

current number of iteration

◆ ~KdTreeBasedKmeansEstimator()

template<typename TKdTree >

itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::~KdTreeBasedKmeansEstimator ( )

overrideprotecteddefault

current number of iteration

Member Function Documentation

◆ CopyParameters() [1/3]

template<typename TKdTree >

void itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::CopyParameters	(	InternalParametersType &	source,
		InternalParametersType &	target
	)

protected

copies the source parameters (k-means) to the target

◆ CopyParameters() [2/3]

template<typename TKdTree >

void itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::CopyParameters	(	InternalParametersType &	source,
		ParametersType &	target
	)

protected

copies the source parameters (k-means) to the target

◆ CopyParameters() [3/3]

template<typename TKdTree >

void itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::CopyParameters	(	ParametersType &	source,
		InternalParametersType &	target
	)

protected

copies the source parameters (k-means) to the target

◆ CreateAnother()

template<typename TKdTree >

virtual::itk::LightObject::Pointer itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::CreateAnother ( ) const

virtual

Create an object from an instance, potentially deferring to a factory. This method allows you to create an instance of an object that is exactly the same type as the referring object. This is useful in cases where an object has been cast back to a base class.

Reimplemented from itk::Object.

◆ FillClusterLabels()

template<typename TKdTree >

void itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::FillClusterLabels	(	KdTreeNodeType *	node,
		int	closestIndex
	)

protected

current number of iteration

◆ Filter()

template<typename TKdTree >

void itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::Filter	(	KdTreeNodeType *	node,
		std::vector< int >	validIndexes,
		MeasurementVectorType &	lowerBound,
		MeasurementVectorType &	upperBound
	)

protected

recursive pruning algorithm. the validIndexes vector contains only the indexes of the surviving candidates for the node

◆ GetCentroidPositionChanges()

template<typename TKdTree >

virtual double itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::GetCentroidPositionChanges ( ) const

virtual

current number of iteration

◆ GetCentroidPositionChangesThreshold()

template<typename TKdTree >

virtual double itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::GetCentroidPositionChangesThreshold ( ) const

virtual

current number of iteration

◆ GetClosestCandidate()

template<typename TKdTree >

int itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::GetClosestCandidate	(	ParameterType &	measurements,
		std::vector< int > &	validIndexes
	)

protected

get the index of the closest candidate to the measurements measurement vector

◆ GetCurrentIteration()

template<typename TKdTree >

virtual int itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::GetCurrentIteration ( ) const

virtual

current number of iteration

◆ GetKdTree()

template<typename TKdTree >

const TKdTree* itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::GetKdTree ( ) const

current number of iteration

◆ GetMaximumIteration()

template<typename TKdTree >

virtual int itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::GetMaximumIteration ( ) const

virtual

current number of iteration

◆ GetMeasurementVectorSize()

template<typename TKdTree >

virtual MeasurementVectorSizeType itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::GetMeasurementVectorSize ( ) const

virtual

Get the length of measurement vectors in the KdTree

◆ GetNameOfClass()

template<typename TKdTree >

virtual const char* itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::GetNameOfClass ( ) const

virtual

Run-time type information (and related methods).

Reimplemented from itk::Object.

◆ GetOutput()

template<typename TKdTree >

const MembershipFunctionVectorObjectType* itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::GetOutput ( ) const

Output Membership function vector containing the membership functions with the final optimized parameters

◆ GetParameters()

template<typename TKdTree >

virtual ParametersType itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::GetParameters ( ) const

virtual

current number of iteration

◆ GetPoint()

template<typename TKdTree >

void itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::GetPoint	(	ParameterType &	point,
		MeasurementVectorType	measurements
	)

protected

imports the measurements measurement vector data to the point

◆ GetSumOfSquaredPositionChanges()

template<typename TKdTree >

double itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::GetSumOfSquaredPositionChanges	(	InternalParametersType &	previous,
		InternalParametersType &	current
	)

protected

gets the sum of squared difference between the previous position and current position of all centroid. This is the primary termination condition for this algorithm. If the return value is less than the value that was set by the SetCentroidPositionChangesThreshold method.

◆ GetUseClusterLabels()

template<typename TKdTree >

virtual bool itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::GetUseClusterLabels ( ) const

virtual

current number of iteration

◆ IsFarther()

template<typename TKdTree >

bool itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::IsFarther	(	ParameterType &	pointA,
		ParameterType &	pointB,
		MeasurementVectorType &	lowerBound,
		MeasurementVectorType &	upperBound
	)

protected

returns true if the pointA is farther than pointB to the boundary

◆ New()

template<typename TKdTree >

static Pointer itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::New ( )

static

Method for creation through the object factory.

◆ PrintPoint()

template<typename TKdTree >

void itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::PrintPoint ( ParameterType & point )

protected

current number of iteration

◆ PrintSelf()

template<typename TKdTree >

void itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::PrintSelf	(	std::ostream &	os,
		Indent	indent
	)		const

overrideprotectedvirtual

current number of iteration

Reimplemented from itk::Object.

◆ SetCentroidPositionChangesThreshold()

template<typename TKdTree >

virtual void itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::SetCentroidPositionChangesThreshold ( double _arg )

virtual

Set/Get the termination threshold for the squared sum of changes in centroid positions after one iteration

◆ SetKdTree()

template<typename TKdTree >

void itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::SetKdTree ( TKdTree * tree )

Set/Get the pointer to the KdTree

◆ SetMaximumIteration()

template<typename TKdTree >

virtual void itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::SetMaximumIteration ( int _arg )

virtual

Set/Get maximum iteration limit.

◆ SetParameters()

template<typename TKdTree >

virtual void itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::SetParameters ( ParametersType _arg )

virtual

Set the position to initialize the optimization.

◆ SetUseClusterLabels()

template<typename TKdTree >

virtual void itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::SetUseClusterLabels ( bool _arg )

virtual

current number of iteration

◆ StartOptimization()

template<typename TKdTree >

void itk::Statistics::KdTreeBasedKmeansEstimator< TKdTree >::StartOptimization ( )

Start optimization Optimization will stop when it meets either of two termination conditions, the maximum iteration limit or epsilon (minimal changes in squared sum of changes in centroid positions)