Finds the threshold value of an image based on maximizing the number of objects in the image that are larger than a given minimal size. More...

#include <itkThresholdMaximumConnectedComponentsImageFilter.h>

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

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

List of all members.

Public Types
typedef SmartPointer< const Self >	ConstPointer
typedef InputImageType::PixelType	InputImagePixelType
typedef InputImageType::ConstPointer	InputImagePointer
typedef InputImageType::RegionType	InputImageRegionType
typedef TInputImage	InputImageType
typedef TInputImage::PixelType	PixelType
typedef SmartPointer< Self >	Pointer
typedef ThresholdMaximumConnectedComponentsImageFilter	Self
typedef ImageToImageFilter < TInputImage, TOutputImage >	Superclass
Public Member Functions
virtual ::itk::LightObject::Pointer	CreateAnother (void) const
virtual const char *	GetNameOfClass () const
virtual SizeValueType	GetNumberOfObjects () const
virtual PixelType	GetThresholdValue () const
	typedef (Concept::Comparable< PixelType >) PixelTypeComparable

virtual void	SetMinimumObjectSizeInPixels (unsigned int _arg)
virtual unsigned int	GetMinimumObjectSizeInPixels () const

virtual void	SetInsideValue (PixelType _arg)
virtual void	SetOutsideValue (PixelType _arg)
virtual void	SetUpperBoundary (PixelType _arg)
virtual PixelType	GetInsideValue () const
virtual PixelType	GetOutsideValue () const
virtual PixelType	GetUpperBoundary () const
Static Public Member Functions
static Pointer	New ()
Protected Member Functions
SizeValueType	ComputeConnectedComponents (void)
void	GenerateData (void)
Private Types
typedef ConnectedComponentImageFilter < OutputImageType, FilterImageType >	ConnectedFilterType
typedef FilterImageType::Pointer	FilterImagePointer
typedef itk::Image < FilterPixelType, itkGetStaticConstMacro(ImageDimension) >	FilterImageType
typedef unsigned int	FilterPixelType
typedef MinimumMaximumImageCalculator < InputImageType >	MinMaxCalculatorType
typedef RelabelComponentImageFilter < FilterImageType, FilterImageType >	RelabelFilterType
typedef BinaryThresholdImageFilter < InputImageType, OutputImageType >	ThresholdFilterType
Private Member Functions
void	operator= (const Self &)
	ThresholdMaximumConnectedComponentsImageFilter (const Self &)
Private Attributes
ConnectedFilterType::Pointer	m_ConnectedComponent
PixelType	m_InsideValue
RelabelFilterType::Pointer	m_LabeledComponent
PixelType	m_LowerBoundary
unsigned int	m_MinimumObjectSizeInPixels
MinMaxCalculatorType::Pointer	m_MinMaxCalculator
SizeValueType	m_NumberOfObjects
PixelType	m_OutsideValue
ThresholdFilterType::Pointer	m_ThresholdFilter
PixelType	m_ThresholdValue
PixelType	m_UpperBoundary
Static Private Attributes
static const unsigned int	ImageDimension = TInputImage::ImageDimension
typedef TOutputImage	OutputImageType
typedef OutputImageType::Pointer	OutputImagePointer
typedef OutputImageType::RegionType	OutputImageRegionType
typedef OutputImageType::PixelType	OutputImagePixelType
	ThresholdMaximumConnectedComponentsImageFilter ()
	~ThresholdMaximumConnectedComponentsImageFilter ()
void	PrintSelf (std::ostream &os, Indent indent) const

Detailed Description

template<class TInputImage, class TOutputImage = TInputImage>
class itk::ThresholdMaximumConnectedComponentsImageFilter< TInputImage, TOutputImage >

Finds the threshold value of an image based on maximizing the number of objects in the image that are larger than a given minimal size.

: This method is based on Topological Stable State Thresholding to calculate the threshold set point. This method is particularly effective when there are a large number of objects in a microscopy image. Uncomment the output statements in the GenerateData section to see how the filter focuses in on a threshold value. Please see the Insight Journal's MICCAI 2005 workshop for a complete description. References are below.

Parameters: The MinimumPixelArea parameter is controlled through the class Get/SetMinimumPixelArea() method. Similar to the standard itk::BinaryThresholdImageFilter the Get/SetInside and Get/SetOutside values of the threshold can be set. The GetNumberOfObjects() and GetThresholdValue() methods return the number of objects above the minimum pixel size and the calculated threshold value.

Automatic Thresholding in ITK: There are multiple methods to automatically calculate the threshold intensity value of an image. As of version 2.6, ITK implements two of these. Otsu thresholding (see itk::OtsuThresholdImageFilter) is a common method for segmenting CT radiographs. Topological Stable State Thresholding works well on images with a large number of objects to be counted.

References:: 1) Urish KL, August J, Huard J. "Unsupervised segmentation for myofiber counting in immunoflourescent images". Insight Journal. ISC/NA-MIC/MICCAI Workshop on Open-Source Software (2005) Dspace handle: http://hdl.handle.net/1926/48 2) Pikaz A, Averbuch, A. "Digital image thresholding based on topological stable-state". Pattern Recognition, 29(5): 829-843, 1996.

: Questions: email Ken Urish at ken.urish(at)gmail.com Please cc the itk list serve for archival purposes.

Definition at line 73 of file itkThresholdMaximumConnectedComponentsImageFilter.h.