itk::HistogramMatchingImageFilter< TInputImage, TOutputImage > Class Template Reference
[Intensity Image Filters, Multithreaded Filters]

Normalize the grayscale values between two image by histogram matching. More...

#include <itkHistogramMatchingImageFilter.h>

Inheritance diagram for itk::HistogramMatchingImageFilter:

[legend]Collaboration diagram for itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >:

[legend]List of all members.

Public Types
typedef HistogramMatchingImageFilter	Self
typedef ImageToImageFilter< TInputImage, TOutputImage >	Superclass
typedef SmartPointer< Self >	Pointer
typedef SmartPointer< const Self >	ConstPointer
typedef TOutputImage::RegionType	OutputImageRegionType
typedef Superclass::InputImageType	InputImageType
typedef Superclass::InputImagePointer	InputImagePointer
typedef Superclass::InputImageConstPointer	InputImageConstPointer
typedef Superclass::OutputImageType	OutputImageType
typedef Superclass::OutputImagePointer	OutputImagePointer
typedef InputImageType::PixelType	InputPixelType
typedef OutputImageType::PixelType	OutputPixelType
typedef Statistics::Histogram< InputPixelType, 1 >	HistogramType
typedef HistogramType::Pointer	HistogramPointer
Public Methods
virtual const char *	GetClassName () const
	itkStaticConstMacro (ImageDimension, unsigned int, TInputImage::ImageDimension)
virtual void	GenerateInputRequestedRegion ()
void	SetSourceImage (const InputImageType *source)
const InputImageType *	GetSourceImage (void)
void	SetReferenceImage (const InputImageType *reference)
const InputImageType *	GetReferenceImage (void)
virtual void	SetNumberOfHistogramLevels (unsigned long _arg)
virtual unsigned long	GetNumberOfHistogramLevels ()
virtual void	SetNumberOfMatchPoints (unsigned long _arg)
virtual unsigned long	GetNumberOfMatchPoints ()
virtual void	SetThresholdAtMeanIntensity (bool _arg)
virtual bool	GetThresholdAtMeanIntensity ()
virtual void	ThresholdAtMeanIntensityOn ()
virtual void	ThresholdAtMeanIntensityOff ()
Static Public Methods
Pointer	New ()
Protected Methods
	HistogramMatchingImageFilter ()
	~HistogramMatchingImageFilter ()
void	PrintSelf (std::ostream &os, Indent indent) const
void	BeforeThreadedGenerateData ()
void	ThreadedGenerateData (const OutputImageRegionType &outputRegionForThread, int threadId)
void	ComputeMinMaxMean (const InputImageType *image, double &minValue, double &maxValue, double &meanValue)
void	ConstructHistogram (const InputImageType *image, HistogramType *histogram, double minValue, double maxValue)

---

Detailed Description

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

Normalize the grayscale values between two image by histogram matching.

HistogramMatchingImageFilter normalizes the grayscale values of a source image based on the grayscale values of a reference image. This filter uses a histogram matching technique where the histograms of the two images are matched only at a specified number of quantile values.

This filter was orginally designed to normalize MR images of the same MR protocol and same body part. The algorithm works best if background pixels are excluded from both the source and reference histograms. A simple background exclusion method is to exclude all pixels whose grayscale values are smaller than the mean grayscale value. ThresholdAtMeanIntensityOn() switches on this simple background exclusion method.

The source image can be set via either SetInput() or SetSourceImage(). The reference image can be set via SetReferenceImage().

SetNumberOfHistogramLevels() sets the number of bins used when creating histograms of the source and reference images. SetNumberOfMatchPoints() governs the number of quantile values to be matched.

This filter assumes that both the source and reference are of the same type and that the input and output image type have the same number of dimension and have scalar pixel types.

Definition at line 60 of file itkHistogramMatchingImageFilter.h.

---

Member Typedef Documentation

template<class TInputImage, class TOutputImage> typedef SmartPointer<const Self> itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::ConstPointer

Reimplemented from itk::ImageToImageFilter< TInputImage, TOutputImage >. Definition at line 68 of file itkHistogramMatchingImageFilter.h.

template<class TInputImage, class TOutputImage> typedef HistogramType::Pointer itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::HistogramPointer

Definition at line 96 of file itkHistogramMatchingImageFilter.h.

template<class TInputImage, class TOutputImage> typedef Statistics::Histogram<InputPixelType, 1> itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::HistogramType

Histogram related typedefs. Definition at line 95 of file itkHistogramMatchingImageFilter.h.

template<class TInputImage, class TOutputImage> typedef Superclass::InputImageConstPointer itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::InputImageConstPointer

Reimplemented from itk::ImageToImageFilter< TInputImage, TOutputImage >. Definition at line 86 of file itkHistogramMatchingImageFilter.h.

template<class TInputImage, class TOutputImage> typedef Superclass::InputImagePointer itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::InputImagePointer

Reimplemented from itk::ImageToImageFilter< TInputImage, TOutputImage >. Definition at line 85 of file itkHistogramMatchingImageFilter.h.

template<class TInputImage, class TOutputImage> typedef Superclass::InputImageType itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::InputImageType

Inherited typedefs. Reimplemented from itk::ImageToImageFilter< TInputImage, TOutputImage >. Definition at line 84 of file itkHistogramMatchingImageFilter.h.

template<class TInputImage, class TOutputImage> typedef InputImageType::PixelType itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::InputPixelType

Pixel related typedefs. Definition at line 91 of file itkHistogramMatchingImageFilter.h.

template<class TInputImage, class TOutputImage> typedef Superclass::OutputImagePointer itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::OutputImagePointer

Reimplemented from itk::ImageSource< TOutputImage >. Definition at line 88 of file itkHistogramMatchingImageFilter.h.

template<class TInputImage, class TOutputImage> typedef TOutputImage::RegionType itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::OutputImageRegionType

Typedef to describe the output image region type. Reimplemented from itk::ImageToImageFilter< TInputImage, TOutputImage >. Definition at line 81 of file itkHistogramMatchingImageFilter.h.

template<class TInputImage, class TOutputImage> typedef Superclass::OutputImageType itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::OutputImageType

Some convenient typedefs. Reimplemented from itk::ImageSource< TOutputImage >. Definition at line 87 of file itkHistogramMatchingImageFilter.h.

template<class TInputImage, class TOutputImage> typedef OutputImageType::PixelType itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::OutputPixelType

Definition at line 92 of file itkHistogramMatchingImageFilter.h.

template<class TInputImage, class TOutputImage> typedef SmartPointer<Self> itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::Pointer

Reimplemented from itk::ImageToImageFilter< TInputImage, TOutputImage >. Definition at line 67 of file itkHistogramMatchingImageFilter.h.

template<class TInputImage, class TOutputImage> typedef HistogramMatchingImageFilter itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::Self

Standard class typedefs. Reimplemented from itk::ImageToImageFilter< TInputImage, TOutputImage >. Definition at line 65 of file itkHistogramMatchingImageFilter.h.

template<class TInputImage, class TOutputImage> typedef ImageToImageFilter<TInputImage,TOutputImage> itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::Superclass

Reimplemented from itk::ImageToImageFilter< TInputImage, TOutputImage >. Definition at line 66 of file itkHistogramMatchingImageFilter.h.

---

Constructor & Destructor Documentation

template<class TInputImage, class TOutputImage> itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::HistogramMatchingImageFilter (    )  [protected]

template<class TInputImage, class TOutputImage> itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::~HistogramMatchingImageFilter (    )  [inline, protected]

Definition at line 135 of file itkHistogramMatchingImageFilter.h. References HardConnectedComponentImageFilter::InputImageType, and HardConnectedComponentImageFilter::InputPixelType.

---

Member Function Documentation

template<class TInputImage, class TOutputImage> void itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::BeforeThreadedGenerateData (  void    )  [protected, virtual]

If an imaging filter needs to perform processing after the buffer has been allocated but before threads are spawned, the filter can can provide an implementation for BeforeThreadedGenerateData(). The execution flow in the default GenerateData() method will be: 1) Allocate the output buffer 2) Call BeforeThreadedGenerateData() 3) Spawn threads, calling ThreadedGenerateData() in each thread. 4) Call AfterThreadedGenerateData() Note that this flow of control is only available if a filter provides a ThreadedGenerateData() method and NOT a GenerateData() method. Reimplemented from itk::ImageSource< TOutputImage >.

template<class TInputImage, class TOutputImage> void itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::ComputeMinMaxMean (  const InputImageType *    image, double &    minValue, double &    maxValue, double &    meanValue )  [protected]

Compute min, max and mean of an image.

template<class TInputImage, class TOutputImage> void itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::ConstructHistogram (  const InputImageType *    image, HistogramType *    histogram, double    minValue, double    maxValue )  [protected]

Construct a histogram from an image.

template<class TInputImage, class TOutputImage> virtual void itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::GenerateInputRequestedRegion (    )  [virtual]

This filter requires all of the input to be in the buffer. Reimplemented from itk::ImageToImageFilter< TInputImage, TOutputImage >.

template<class TInputImage, class TOutputImage> virtual const char* itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::GetClassName (    )  const [virtual]

Run-time type information (and related methods). Reimplemented from itk::ImageToImageFilter< TInputImage, TOutputImage >.

template<class TInputImage, class TOutputImage> virtual unsigned long itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::GetNumberOfHistogramLevels (    )  [virtual]

Set/Get the number of histogram levels used.

template<class TInputImage, class TOutputImage> virtual unsigned long itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::GetNumberOfMatchPoints (    )  [virtual]

Set/Get the number of match points used.

template<class TInputImage, class TOutputImage> const InputImageType* itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::GetReferenceImage (  void    )

Set/Get the reference image.

template<class TInputImage, class TOutputImage> const InputImageType* itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::GetSourceImage (  void    )  [inline]

Set/Get the source image. Definition at line 101 of file itkHistogramMatchingImageFilter.h. References HardConnectedComponentImageFilter::InputImageType.

template<class TInputImage, class TOutputImage> virtual bool itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::GetThresholdAtMeanIntensity (    )  [virtual]

Set/Get the threshold at mean intensity flag. If true, only source (reference) pixels which are greater than the mean source (reference) intensity is used in the histogram matching. If false, all pixels are used.

template<class TInputImage, class TOutputImage> itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::itkStaticConstMacro (  ImageDimension   , unsigned    int, TInputImage::ImageDimension    )

ImageDimension enumeration. Reimplemented from itk::ImageToImageFilter< TInputImage, TOutputImage >.

template<class TInputImage, class TOutputImage> Pointer itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::New (    )  [static]

Method for creation through the object factory. Reimplemented from itk::Object.

template<class TInputImage, class TOutputImage> void itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::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::ImageToImageFilter< TInputImage, TOutputImage >.

template<class TInputImage, class TOutputImage> virtual void itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::SetNumberOfHistogramLevels (  unsigned long    _arg )  [virtual]

Set/Get the number of histogram levels used.

template<class TInputImage, class TOutputImage> virtual void itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::SetNumberOfMatchPoints (  unsigned long    _arg )  [virtual]

Set/Get the number of match points used.

template<class TInputImage, class TOutputImage> void itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::SetReferenceImage (  const InputImageType *    reference )

Set/Get the reference image.

template<class TInputImage, class TOutputImage> void itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::SetSourceImage (  const InputImageType *    source )  [inline]

Set/Get the source image. Definition at line 99 of file itkHistogramMatchingImageFilter.h. References HardConnectedComponentImageFilter::InputImageType.

template<class TInputImage, class TOutputImage> virtual void itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::SetThresholdAtMeanIntensity (  bool    _arg )  [virtual]

Set/Get the threshold at mean intensity flag. If true, only source (reference) pixels which are greater than the mean source (reference) intensity is used in the histogram matching. If false, all pixels are used.

template<class TInputImage, class TOutputImage> void itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::ThreadedGenerateData (  const OutputImageRegionType &    outputRegionForThread, int    threadId )  [protected, virtual]

If an imaging filter can be implemented as a multithreaded algorithm, the filter will provide an implementation of ThreadedGenerateData(). This superclass will automatically split the output image into a number of pieces, spawn multiple threads, and call ThreadedGenerateData() in each thread. Prior to spawning threads, the BeforeThreadedGenerateData() method is called. After all the threads have completed, the AfterThreadedGenerateData() method is called. If an image processing filter cannot support threading, that filter should provide an implementation of the GenerateData() method instead of providing an implementation of ThreadedGenerateData(). If a filter provides a GenerateData() method as its implementation, then the filter is responsible for allocating the output data. If a filter provides a ThreadedGenerateData() method as its implementation, then the output memory will allocated automatically by this superclass. The ThreadedGenerateData() method should only produce the output specified by "outputThreadRegion" parameter. ThreadedGenerateData() cannot write to any other portion of the output image (as this is responsibility of a different thread). See also: GenerateData(), SplitRequestedRegion() Reimplemented from itk::ImageSource< TOutputImage >.

template<class TInputImage, class TOutputImage> virtual void itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::ThresholdAtMeanIntensityOff (    )  [virtual]

Set/Get the threshold at mean intensity flag. If true, only source (reference) pixels which are greater than the mean source (reference) intensity is used in the histogram matching. If false, all pixels are used.

template<class TInputImage, class TOutputImage> virtual void itk::HistogramMatchingImageFilter< TInputImage, TOutputImage >::ThresholdAtMeanIntensityOn (    )  [virtual]

Set/Get the threshold at mean intensity flag. If true, only source (reference) pixels which are greater than the mean source (reference) intensity is used in the histogram matching. If false, all pixels are used.

---

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

• itkHistogramMatchingImageFilter.h

---