itk::CurvatureFlowImageFilter< TInputImage, TOutputImage > Class Template Reference
[Image Enhancement Filters, Multithreaded Filters, Filters supporting Streaming]

Denoise an image using curvature driven flow. More...

#include <itkCurvatureFlowImageFilter.h>

Inheritance diagram for itk::CurvatureFlowImageFilter:

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

[legend]List of all members.

Public Types
typedef CurvatureFlowImageFilter	Self
typedef DenseFiniteDifferenceImageFilter< TInputImage, TOutputImage >	Superclass
typedef SmartPointer< Self >	Pointer
typedef SmartPointer< const Self >	ConstPointer
typedef Superclass::InputImageType	InputImageType
typedef Superclass::OutputImageType	OutputImageType
typedef OutputImageType::Pointer	OutputImagePointer
typedef Superclass::FiniteDifferenceFunctionType	FiniteDifferenceFunctionType
typedef CurvatureFlowFunction< OutputImageType >	CurvatureFlowFunctionType
typedef Superclass::PixelType	PixelType
typedef Superclass::TimeStepType	TimeStepType
Public Methods
virtual const char *	GetClassName () const
	itkStaticConstMacro (ImageDimension, unsigned int, Superclass::ImageDimension)
virtual void	SetNumberOfIterations (unsigned int _arg)
virtual unsigned int	GetNumberOfIterations ()
virtual void	SetTimeStep (TimeStepType _arg)
virtual TimeStepType	GetTimeStep ()
Static Public Methods
Pointer	New ()
Protected Methods
	CurvatureFlowImageFilter ()
	~CurvatureFlowImageFilter ()
void	PrintSelf (std::ostream &os, Indent indent) const
virtual void	InitializeIteration ()
virtual void	EnlargeOutputRequestedRegion (DataObject *)
virtual void	GenerateInputRequestedRegion ()
virtual bool	Halt ()

---

Detailed Description

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

Denoise an image using curvature driven flow.

CurvatureFlowImageFilter implements a curvature driven image denoising algorithm. Iso-brightness contours in the grayscale input image are viewed as a level set. The level set is then evolved using a curvature-based speed function:

where is the curvature.

The advantage of this approach is that sharp boundaries are preserved with smoothing occuring only within a region. However, it should be noted that continuous application of this scheme will result in the eventual removal of all information as each contour shrinks to zero and disappear.

Note that unlike level set segmentation algorithms, the image to be denoised is already the level set and can be set directly as the input using the SetInput() method.

This filter has two parameters: the number of update iterations to be performed and the timestep between each update.

The timestep should be "small enough" to ensure numerical stability. Stability is guarantee when the timestep meets the CFL (Courant-Friedrichs-Levy) condition. Broadly speaking, this condition ensures that each contour does not move more than one grid position at each timestep. In the literature, the timestep is typically user specified and have to manually tuned to the application.

This filter make use of the multi-threaded finite difference solver hierarchy. Updates are computed using a CurvatureFlowFunction object. A zero flux Neumann boundary condition when computing derivatives near the data boundary.

This filter may be streamed. To support streaming this filter produces a padded output which takes into account edge effects. The size of the padding is m_NumberOfIterations on each edge. Users of this filter should only make use of the center valid central region.

Warning:

This filter assumes that the input and output types have the same dimensions. This filter also requires that the output image pixels are of a floating point type. This filter works for any dimensional images.

Reference: "Level Set Methods and Fast Marching Methods", J.A. Sethian, Cambridge Press, Chapter 16, Second edition, 1999.

See also:

DenseFiniteDifferenceImageFilter , CurvatureFlowFunction , MinMaxCurvatureFlowImageFilter , BinaryMinMaxCurvatureFlowImageFilter

Input/Output Restrictions: TInputImage and TOutputImage must have the same dimension. TOutputImage's pixel type must be a real number type.

Definition at line 88 of file itkCurvatureFlowImageFilter.h.

---

Member Typedef Documentation

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

Reimplemented from itk::ImageToImageFilter< TInputImage, TOutputImage >. Reimplemented in itk::BinaryMinMaxCurvatureFlowImageFilter< TInputImage, TOutputImage >, and itk::MinMaxCurvatureFlowImageFilter< TInputImage, TOutputImage >. Definition at line 97 of file itkCurvatureFlowImageFilter.h.

template<class TInputImage, class TOutputImage> typedef CurvatureFlowFunction<OutputImageType> itk::CurvatureFlowImageFilter< TInputImage, TOutputImage >::CurvatureFlowFunctionType

CurvatureFlowFunction type. Definition at line 119 of file itkCurvatureFlowImageFilter.h.

template<class TInputImage, class TOutputImage> typedef Superclass::FiniteDifferenceFunctionType itk::CurvatureFlowImageFilter< TInputImage, TOutputImage >::FiniteDifferenceFunctionType

FiniteDifferenceFunction type. Reimplemented from itk::DenseFiniteDifferenceImageFilter< TInputImage, TOutputImage >. Reimplemented in itk::BinaryMinMaxCurvatureFlowImageFilter< TInputImage, TOutputImage >, and itk::MinMaxCurvatureFlowImageFilter< TInputImage, TOutputImage >. Definition at line 115 of file itkCurvatureFlowImageFilter.h.

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

InputImage type. Reimplemented from itk::DenseFiniteDifferenceImageFilter< TInputImage, TOutputImage >. Definition at line 107 of file itkCurvatureFlowImageFilter.h.

template<class TInputImage, class TOutputImage> typedef OutputImageType::Pointer itk::CurvatureFlowImageFilter< TInputImage, TOutputImage >::OutputImagePointer

Reimplemented from itk::ImageSource< TOutputImage >. Definition at line 111 of file itkCurvatureFlowImageFilter.h.

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

OutputImage type. Reimplemented from itk::DenseFiniteDifferenceImageFilter< TInputImage, TOutputImage >. Reimplemented in itk::BinaryMinMaxCurvatureFlowImageFilter< TInputImage, TOutputImage >, and itk::MinMaxCurvatureFlowImageFilter< TInputImage, TOutputImage >. Definition at line 110 of file itkCurvatureFlowImageFilter.h.

template<class TInputImage, class TOutputImage> typedef Superclass::PixelType itk::CurvatureFlowImageFilter< TInputImage, TOutputImage >::PixelType

The pixel type of the output image will be used in computations. Inherited from the superclass. Reimplemented from itk::DenseFiniteDifferenceImageFilter< TInputImage, TOutputImage >. Definition at line 127 of file itkCurvatureFlowImageFilter.h.

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

Reimplemented from itk::ImageToImageFilter< TInputImage, TOutputImage >. Reimplemented in itk::BinaryMinMaxCurvatureFlowImageFilter< TInputImage, TOutputImage >, and itk::MinMaxCurvatureFlowImageFilter< TInputImage, TOutputImage >. Definition at line 96 of file itkCurvatureFlowImageFilter.h.

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

Standard class typedefs. Reimplemented from itk::DenseFiniteDifferenceImageFilter< TInputImage, TOutputImage >. Reimplemented in itk::BinaryMinMaxCurvatureFlowImageFilter< TInputImage, TOutputImage >, and itk::MinMaxCurvatureFlowImageFilter< TInputImage, TOutputImage >. Definition at line 93 of file itkCurvatureFlowImageFilter.h.

template<class TInputImage, class TOutputImage> typedef DenseFiniteDifferenceImageFilter<TInputImage, TOutputImage> itk::CurvatureFlowImageFilter< TInputImage, TOutputImage >::Superclass

Reimplemented from itk::DenseFiniteDifferenceImageFilter< TInputImage, TOutputImage >. Reimplemented in itk::BinaryMinMaxCurvatureFlowImageFilter< TInputImage, TOutputImage >, and itk::MinMaxCurvatureFlowImageFilter< TInputImage, TOutputImage >. Definition at line 95 of file itkCurvatureFlowImageFilter.h.

template<class TInputImage, class TOutputImage> typedef Superclass::TimeStepType itk::CurvatureFlowImageFilter< TInputImage, TOutputImage >::TimeStepType

The time step type. Inherited from the superclass. Reimplemented from itk::DenseFiniteDifferenceImageFilter< TInputImage, TOutputImage >. Definition at line 130 of file itkCurvatureFlowImageFilter.h.

---

Constructor & Destructor Documentation

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

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

Definition at line 146 of file itkCurvatureFlowImageFilter.h.

---

Member Function Documentation

template<class TInputImage, class TOutputImage> virtual void itk::CurvatureFlowImageFilter< TInputImage, TOutputImage >::EnlargeOutputRequestedRegion (  DataObject *    )  [protected, virtual]

To support streaming, this filter produces a output which is larger than the original requested region. The output is padding by m_NumberOfIterations pixels on edge. Reimplemented from itk::ProcessObject.

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

Edge effects are taken care of by padding the output requested region. As such, the input requested region needs to at minimum the same size as the output requested region. Reimplemented from itk::FiniteDifferenceImageFilter< TInputImage, TOutputImage >.

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

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

template<class TInputImage, class TOutputImage> virtual unsigned int itk::CurvatureFlowImageFilter< TInputImage, TOutputImage >::GetNumberOfIterations (    )  [virtual]

Get the number of iterations to be performed.

template<class TInputImage, class TOutputImage> virtual TimeStepType itk::CurvatureFlowImageFilter< TInputImage, TOutputImage >::GetTimeStep (    )  [virtual]

Get the timestep parameter.

template<class TInputImage, class TOutputImage> virtual bool itk::CurvatureFlowImageFilter< TInputImage, TOutputImage >::Halt (    )  [inline, protected, virtual]

Supplies the halting criteria for this class of filters. The algorithm will stop after a user-specified number of iterations. Implements itk::FiniteDifferenceImageFilter< TInputImage, TOutputImage >. Definition at line 151 of file itkCurvatureFlowImageFilter.h. References itk::FiniteDifferenceImageFilter< TInputImage, TOutputImage >::GetElapsedIterations().

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

Initialize the state of filter and equation before each iteration. Progress feeback is implemented as part of this method. Reimplemented from itk::FiniteDifferenceImageFilter< TInputImage, TOutputImage >. Reimplemented in itk::BinaryMinMaxCurvatureFlowImageFilter< TInputImage, TOutputImage >, and itk::MinMaxCurvatureFlowImageFilter< TInputImage, TOutputImage >.

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

Dimensionality of input and output data is assumed to be the same. It is inherited from the superclass. Reimplemented from itk::DenseFiniteDifferenceImageFilter< TInputImage, TOutputImage >. Reimplemented in itk::BinaryMinMaxCurvatureFlowImageFilter< TInputImage, TOutputImage >, and itk::MinMaxCurvatureFlowImageFilter< TInputImage, TOutputImage >.

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

Method for creation through the object factory. Reimplemented from itk::ImageToImageFilter< TInputImage, TOutputImage >. Reimplemented in itk::BinaryMinMaxCurvatureFlowImageFilter< TInputImage, TOutputImage >, and itk::MinMaxCurvatureFlowImageFilter< TInputImage, TOutputImage >.

template<class TInputImage, class TOutputImage> void itk::CurvatureFlowImageFilter< 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::DenseFiniteDifferenceImageFilter< TInputImage, TOutputImage >. Reimplemented in itk::BinaryMinMaxCurvatureFlowImageFilter< TInputImage, TOutputImage >, and itk::MinMaxCurvatureFlowImageFilter< TInputImage, TOutputImage >.

template<class TInputImage, class TOutputImage> virtual void itk::CurvatureFlowImageFilter< TInputImage, TOutputImage >::SetNumberOfIterations (  unsigned int    _arg )  [virtual]

Set the number of iterations to be performed.

template<class TInputImage, class TOutputImage> virtual void itk::CurvatureFlowImageFilter< TInputImage, TOutputImage >::SetTimeStep (  TimeStepType    _arg )  [virtual]

Set the timestep parameter.

---

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

• itkCurvatureFlowImageFilter.h

---