Label pixels that are connected to one set of seeds but not another. More...

#include <itkIsolatedConnectedImageFilter.h>

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

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

Public Types
typedef SmartPointer< const Self >	ConstPointer
typedef InputImageType::IndexType	IndexType
typedef InputImageType::ConstPointer	InputImageConstPointer
typedef InputImageType::PixelType	InputImagePixelType
typedef InputImageType::Pointer	InputImagePointer
typedef InputImageType::RegionType	InputImageRegionType
typedef TInputImage	InputImageType
typedef NumericTraits < InputImagePixelType > ::RealType	InputRealType
typedef OutputImageType::PixelType	OutputImagePixelType
typedef OutputImageType::Pointer	OutputImagePointer
typedef OutputImageType::RegionType	OutputImageRegionType
typedef TOutputImage	OutputImageType
typedef SmartPointer< Self >	Pointer
typedef std::vector< IndexType >	SeedsContainerType
typedef IsolatedConnectedImageFilter	Self
typedef InputImageType::SizeType	SizeType
typedef ImageToImageFilter < TInputImage, TOutputImage >	Superclass
Public Member Functions
void	AddSeed1 (const IndexType &seed)
void	AddSeed2 (const IndexType &seed)
void	ClearSeeds1 ()
void	ClearSeeds2 ()
virtual ::itk::LightObject::Pointer	CreateAnother (void) const
virtual const InputImagePixelType &	GetIsolatedValue ()
virtual const char *	GetNameOfClass () const
virtual const bool &	GetThresholdingFailed ()
InputImagePixelType	GetUpperValueLimit ()
void	PrintSelf (std::ostream &os, Indent indent) const
void	SetSeed1 (const IndexType &seed)
void	SetSeed2 (const IndexType &seed)
void	SetUpperValueLimit (InputImagePixelType upperValue)
	typedef (Concept::HasNumericTraits< InputImagePixelType >) InputHasNumericTraitsCheck

virtual const SeedsContainerType &	GetSeeds1 () const
virtual const SeedsContainerType &	GetSeeds2 () const

virtual void	SetLower (InputImagePixelType _arg)
virtual const InputImagePixelType &	GetLower ()

virtual void	SetUpper (InputImagePixelType _arg)
virtual const InputImagePixelType &	GetUpper ()

virtual void	SetIsolatedValueTolerance (InputImagePixelType _arg)
virtual const InputImagePixelType &	GetIsolatedValueTolerance ()

virtual void	SetReplaceValue (OutputImagePixelType _arg)
virtual const OutputImagePixelType &	GetReplaceValue ()

virtual void	SetFindUpperThreshold (bool _arg)
virtual void	FindUpperThresholdOn ()
virtual void	FindUpperThresholdOff ()
virtual const bool &	GetFindUpperThreshold ()
Static Public Member Functions
static Pointer	New ()
Protected Member Functions
void	EnlargeOutputRequestedRegion (DataObject *output)
void	GenerateData ()
void	GenerateInputRequestedRegion ()
Protected Attributes
bool	m_FindUpperThreshold
InputImagePixelType	m_IsolatedValue
InputImagePixelType	m_IsolatedValueTolerance
InputImagePixelType	m_Lower
OutputImagePixelType	m_ReplaceValue
bool	m_ThresholdingFailed
InputImagePixelType	m_Upper
Private Member Functions
	IsolatedConnectedImageFilter (const Self &)
void	operator= (const Self &)
SeedsContainerType	m_Seeds1
SeedsContainerType	m_Seeds2
	IsolatedConnectedImageFilter ()
	~IsolatedConnectedImageFilter ()

Detailed Description

template<class TInputImage, class TOutputImage>
class itk::IsolatedConnectedImageFilter< TInputImage, TOutputImage >

Label pixels that are connected to one set of seeds but not another.

IsolatedConnectedImageFilter finds the optimal threshold to separate two regions. It has two modes, one to separate dark regions surrounded by bright regions by automatically finding a minimum isolating upper threshold, and another to separate bright regions surrounded by dark regions by automatically finding a maximum lower isolating threshold. The mode can be chosen by setting FindUpperThresholdOn()/Off(). In both cases, the isolating threshold is retrieved with GetIsolatedValue().

The algorithm labels pixels with ReplaceValue that are connected to Seeds1 AND NOT connected to Seeds2. When finding the threshold to separate two dark regions surrounded by bright regions, given a fixed lower threshold, the filter adjusts the upper threshold until the two sets of seeds are not connected. The algorithm uses a binary search to adjust the upper threshold, starting at Upper. The reverse is true for finding the threshold to separate two bright regions. Lower defaults to the smallest possible value for the InputImagePixelType, and Upper defaults to the largest possible value for the InputImagePixelType.

The user can also supply the Lower and Upper values to restrict the search. However, if the range is too restrictive, it could happen that no isolating threshold can be found between the user specified Lower and Upper values. Therefore, unless the user is sure of the bounds to set, it is recommended that the user set these values to the lowest and highest intensity values in the image, respectively.

The user can specify more than one seed for both regions to separate. The algorithm will try find the threshold that ensures that all of the first seeds are contained in the resulting segmentation and all of the second seeds are not contained in the segmentation.

It is possible that the algorithm may not be able to find the isolating threshold because no such threshold exists. The user can check for this by querying the GetThresholdingFailed() flag.

Definition at line 71 of file itkIsolatedConnectedImageFilter.h.