Main Page Groups Namespace List Class Hierarchy Alphabetical List Compound List File List Namespace Members Compound Members File Members Concepts

itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage > Class Template Reference
[Image Gradient Filters]

Computes a scalar, gradient magnitude image from a multiple channel (pixels are vectors) input. More...

#include <itkVectorGradientMagnitudeImageFilter.h>

Inheritance diagram for itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >:

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

[legend]List of all members.


Public Types
typedef VectorGradientMagnitudeImageFilter	Self
typedef ImageToImageFilter< TInputImage, TOutputImage >	Superclass
typedef SmartPointer< Self >	Pointer
typedef SmartPointer< const Self >	ConstPointer
typedef TOutputImage::PixelType	OutputPixelType
typedef TInputImage::PixelType	InputPixelType
typedef TInputImage	InputImageType
typedef TOutputImage	OutputImageType
typedef InputImageType::Pointer	InputImagePointer
typedef OutputImageType::Pointer	OutputImagePointer
typedef TRealType	RealType
typedef Vector< TRealType, ::itk::GetVectorDimension< InputPixelType >::VectorDimension >	RealVectorType
typedef Image< RealVectorType, ::itk::GetImageDimension< TInputImage >::ImageDimension >	RealVectorImageType
typedef ConstNeighborhoodIterator< RealVectorImageType >	ConstNeighborhoodIteratorType
typedef Superclass::OutputImageRegionType	OutputImageRegionType
Public Member Functions
virtual const char *	GetClassName () const
	itkStaticConstMacro (ImageDimension, unsigned int, TOutputImage::ImageDimension)
	itkStaticConstMacro (VectorDimension, unsigned int, InputPixelType::Dimension)
virtual void	GenerateInputRequestedRegion () throw (InvalidRequestedRegionError)
void	SetUseImageSpacingOn ()
void	SetUseImageSpacingOff ()

void	SetUseImageSpacing (bool)
virtual bool	GetUseImageSpacing ()

void	SetDerivativeWeights (TRealType data[])
virtual const TRealType *	GetDerivativeWeights () const

virtual void	SetComponentWeights (TRealType data[])
virtual const TRealType *	GetComponentWeights () const

virtual void	SetUsePrincipleComponents (bool _arg)
virtual bool	GetUsePrincipleComponents ()
void	SetUsePrincipleComponentsOn ()
void	SetUsePrincipleComponentsOff ()
Static Public Member Functions
Pointer	New ()
int	CubicSolver (double , double )
Protected Member Functions
	VectorGradientMagnitudeImageFilter ()
virtual	~VectorGradientMagnitudeImageFilter ()
void	BeforeThreadedGenerateData ()
void	ThreadedGenerateData (const OutputImageRegionType &outputRegionForThread, int threadId)
void	PrintSelf (std::ostream &os, Indent indent) const
TRealType	NonPCEvaluateAtNeighborhood (const ConstNeighborhoodIteratorType &it) const
TRealType	EvaluateAtNeighborhood3D (const ConstNeighborhoodIteratorType &it) const
TRealType	EvaluateAtNeighborhood (const ConstNeighborhoodIteratorType &it) const
Protected Attributes
TRealType	m_DerivativeWeights [itk::GetImageDimension< TInputImage >::ImageDimension]
TRealType	m_ComponentWeights [itk::GetVectorDimension< InputPixelType >::VectorDimension]
TRealType	m_SqrtComponentWeights [itk::GetVectorDimension< InputPixelType >::VectorDimension]

Detailed Description

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>
class itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >

Computes a scalar, gradient magnitude image from a multiple channel (pixels are vectors) input.

Overview: This filter has two calculation modes. The first (default) mode calculates gradient magnitude as the difference between the largest two eigenvalues in a principle component analysis of the partial derivatives [1]. The gradient is then based on the direction of maximal change, and is a characterization of how "elongated" the point-spread of the analysis is found to be.

The second, more heuristic, calculation mode finds gradient magnitude as the square-root of the sum of the * individual weighted vector component derivative sums squared. That is, * $\mathbf{magnitude} = \left( \sum_{i=0}^n \sum_{j=0}^m \frac{\delta * \phi_j}{\delta \mathbf{x}_{i}}^2 \right)^{\frac{1}{2}}$ , where $\phi_j$ * is the $j^{\mathbf{th}}$ channel of vector image $\phi$ of dimension $n$

. * Weighting terms are applied to each vector component.

The second mode is computationally much faster than the first and has the advantage that it is automatically multi-threaded (some vnl functions used in the first mode are not thread-safe). The first mode, however, tends to give intuitively better results with less (or no) parameter tuning.

Template Parameters (Input and Output): This filter has one required template parameter which defines the input image type. The pixel type of the input image is assumed to be a vector (e.g., itk::Vector, itk::RGBPixel, itk::FixedArray). The scalar type of the vector components must be castable to floating point. Instantiating with an image of RGBPixel<unsigned short>, for example, is allowed, but the filter will convert it to an image of Vector<float,3> for processing.

The second template parameter, TRealType, can be optionally specified to define the scalar numerical type used in calculations. This is the component type of the output image, which will be of itk::Vector<TRealType, N>, where N is the number of channels in the multiple component input image. The default type of TRealType is float. For extra precision, you may safely change this parameter to double.

The third template parameter is the output image type. The third parameter will be automatically constructed from the first and second parameters, so it is not necessary (or advisable) to set this parameter explicitly. Given an M-channel input image with dimensionality N, and a numerical type specified as TRealType, the output image will be of type itk::Image<itk::Vector<TRealType, M>, N>.

Filter Parameters: The methods Set/GetUsePrincipleComponents and SetUsePrincipleComponentsOn/Off determine controls the calculation mode that is used.

The method SetUseImageSpacingOn will cause derivatives in the image to be scaled (inversely) with the pixel size of the input image, effectively taking derivatives in world coordinates (versus isotropic image space). SetUseImageSpacingOff turns this functionality off. Default is UseImageSpacingOff (all weights are 1.0). The parameter UseImageSpacing can be set directly with the method SetUseImageSpacing(bool).

Weights can be applied to the derivatives directly using the SetDerivativeWeights method. Note that if UseImageSpacing is set to TRUE (ON), then these weights will be overridden by weights derived from the image spacing when the filter is updated. The argument to this method is a C array of TRealValue type.

Weights can be applied to each vector component of the image when the component derivative values are summed during computation. Specify these weights using the SetComponentWeights method. The argument to this method is a C array of TRealValue type.

Constraints: The filter requires an image with at least two dimensions and a vector length of at least 2. The theory supports extension to scalar images, but the implementation of the itk vector classes do not

The template parameter TRealType must be floating point (float or double) or a user-defined "real" numerical type with arithmetic operations defined sufficient to compute derivatives.

Performance: This filter will automatically multithread if run with SetUsePrincipleComponents=Off or on 3D data in UsePrincipleComponents=On mode. Unfortunately the ND eigen solver used is not thread safe (a special 3D solver is), so it cannot multithread for data other than 3D in UsePrincipleComponents=On mode.

References

[1] G. Sapiro and D. Ringach, "Anisotropic Diffusion of Multivalued Images with Application to Color Filtering," IEEE Transactions on Image Processing, Vol 5, No. 11 pp. 1582-1586, 1996

See also:

Definition at line 137 of file itkVectorGradientMagnitudeImageFilter.h.

Member Typedef Documentation

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

typedef ConstNeighborhoodIterator<RealVectorImageType> itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::ConstNeighborhoodIteratorType

Type of the iterator that will be used to move through the image. Also the type which will be passed to the evaluate function Definition at line 180 of file itkVectorGradientMagnitudeImageFilter.h.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

typedef SmartPointer<const Self> itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::ConstPointer

Reimplemented from itk::ImageToImageFilter< TInputImage, TOutputImage >.
Definition at line 145 of file itkVectorGradientMagnitudeImageFilter.h.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

typedef InputImageType::Pointer itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::InputImagePointer

Reimplemented from itk::ImageToImageFilter< TInputImage, TOutputImage >.
Definition at line 161 of file itkVectorGradientMagnitudeImageFilter.h.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

typedef TInputImage itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::InputImageType

Image typedef support
Reimplemented from itk::ImageToImageFilter< TInputImage, TOutputImage >.
Definition at line 159 of file itkVectorGradientMagnitudeImageFilter.h.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

typedef TInputImage::PixelType itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::InputPixelType

Definition at line 156 of file itkVectorGradientMagnitudeImageFilter.h.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

typedef OutputImageType::Pointer itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::OutputImagePointer

Reimplemented from itk::ImageSource< TOutputImage >.
Definition at line 162 of file itkVectorGradientMagnitudeImageFilter.h.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

typedef Superclass::OutputImageRegionType itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::OutputImageRegionType

Superclass typedefs.
Reimplemented from itk::ImageToImageFilter< TInputImage, TOutputImage >.
Definition at line 183 of file itkVectorGradientMagnitudeImageFilter.h.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

typedef TOutputImage itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::OutputImageType

Some convenient typedefs.
Reimplemented from itk::ImageSource< TOutputImage >.
Definition at line 160 of file itkVectorGradientMagnitudeImageFilter.h.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

typedef TOutputImage::PixelType itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::OutputPixelType

Extract some information from the image types. Dimensionality of the two images is assumed to be the same. Definition at line 155 of file itkVectorGradientMagnitudeImageFilter.h.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

typedef SmartPointer<Self> itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::Pointer

Reimplemented from itk::ImageToImageFilter< TInputImage, TOutputImage >.
Definition at line 144 of file itkVectorGradientMagnitudeImageFilter.h.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

typedef TRealType itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::RealType

Define the data type and the vector of data type used in calculations. Definition at line 173 of file itkVectorGradientMagnitudeImageFilter.h.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

typedef Image<RealVectorType, ::itk::GetImageDimension<TInputImage>::ImageDimension> itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::RealVectorImageType

Definition at line 175 of file itkVectorGradientMagnitudeImageFilter.h.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

typedef Vector<TRealType, ::itk::GetVectorDimension<InputPixelType>::VectorDimension> itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::RealVectorType

Definition at line 174 of file itkVectorGradientMagnitudeImageFilter.h.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

typedef VectorGradientMagnitudeImageFilter itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::Self

Standard class typedefs.
Reimplemented from itk::ImageToImageFilter< TInputImage, TOutputImage >.
Definition at line 142 of file itkVectorGradientMagnitudeImageFilter.h.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

typedef ImageToImageFilter< TInputImage, TOutputImage > itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::Superclass

Reimplemented from itk::ImageToImageFilter< TInputImage, TOutputImage >.
Definition at line 143 of file itkVectorGradientMagnitudeImageFilter.h.

Constructor & Destructor Documentation

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::VectorGradientMagnitudeImageFilter ( ) [protected]

Member Function Documentation

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

int itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::CubicSolver ( double * ,

double *

) [static]

A specialized solver for finding the roots of a cubic polynomial. Necessary to multi-thread the 3D case

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

TRealType itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::EvaluateAtNeighborhood ( const ConstNeighborhoodIteratorType & it ) const [inline, protected]

Definition at line 389 of file itkVectorGradientMagnitudeImageFilter.h.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

TRealType itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::EvaluateAtNeighborhood3D ( const ConstNeighborhoodIteratorType & it ) const [inline, protected]

Definition at line 290 of file itkVectorGradientMagnitudeImageFilter.h.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

virtual void itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::GenerateInputRequestedRegion ( ) throw (InvalidRequestedRegionError) [virtual]

VectorGradientMagnitudeImageFilter needs a larger input requested region than the output requested region (larger by the kernel size to calculate derivatives). As such, VectorGradientMagnitudeImageFilter needs to provide an implementation for GenerateInputRequestedRegion() in order to inform the pipeline execution model.

See also:
ImageToImageFilter::GenerateInputRequestedRegion()

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

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

virtual bool itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::GetUsePrincipleComponents ( ) [virtual]

Set/Get principle components calculation mode. When this is set to TRUE/ON, the gradient calculation will involve a priniciple component analysis of the partial derivatives of the color components. When this value is set to FALSE/OFF, the calculation is done as a square root of weighted sum of the derivatives squared. Default is UsePrincipleComponents = true.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::itkStaticConstMacro ( VectorDimension ,

unsigned int,

InputPixelType::Dimension

)

Length of the vector pixel type of the input image.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::itkStaticConstMacro ( ImageDimension ,

unsigned int,

TOutputImage::ImageDimension

)

The dimensionality of the input and output images.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

Pointer itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::New ( ) [static]

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

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

TRealType itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::NonPCEvaluateAtNeighborhood ( const ConstNeighborhoodIteratorType & it ) const [inline, protected]

Definition at line 271 of file itkVectorGradientMagnitudeImageFilter.h.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

virtual void itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::SetUsePrincipleComponents ( bool _arg ) [virtual]

Set/Get principle components calculation mode. When this is set to TRUE/ON, the gradient calculation will involve a priniciple component analysis of the partial derivatives of the color components. When this value is set to FALSE/OFF, the calculation is done as a square root of weighted sum of the derivatives squared. Default is UsePrincipleComponents = true.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

void itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::SetUsePrincipleComponentsOff ( ) [inline]

Set/Get principle components calculation mode. When this is set to TRUE/ON, the gradient calculation will involve a priniciple component analysis of the partial derivatives of the color components. When this value is set to FALSE/OFF, the calculation is done as a square root of weighted sum of the derivatives squared. Default is UsePrincipleComponents = true. Definition at line 236 of file itkVectorGradientMagnitudeImageFilter.h.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

void itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::SetUsePrincipleComponentsOn ( ) [inline]

Set/Get principle components calculation mode. When this is set to TRUE/ON, the gradient calculation will involve a priniciple component analysis of the partial derivatives of the color components. When this value is set to FALSE/OFF, the calculation is done as a square root of weighted sum of the derivatives squared. Default is UsePrincipleComponents = true. Definition at line 232 of file itkVectorGradientMagnitudeImageFilter.h.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

void itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::ThreadedGenerateData ( const OutputImageRegionType & outputRegionForThread,

int threadId

) [protected, virtual]

VectorGradientMagnitudeImageFilter can be implemented as a multithreaded filter. Therefore, this implementation provides a ThreadedGenerateData() routine which is called for each processing thread. The output image data is allocated automatically by the superclass prior to calling ThreadedGenerateData(). ThreadedGenerateData can only write to the portion of the output image specified by the parameter "outputRegionForThread"

See also:
ImageToImageFilter::ThreadedGenerateData(), ImageToImageFilter::GenerateData()

Reimplemented from itk::ImageSource< TOutputImage >.

Member Data Documentation

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

TRealType itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::m_ComponentWeights[itk::GetVectorDimension< InputPixelType >::VectorDimension] [protected]

These weights are used to scale vector component values when they are combined to produce a scalar. The square roon Definition at line 428 of file itkVectorGradientMagnitudeImageFilter.h.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

TRealType itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::m_DerivativeWeights[itk::GetImageDimension< TInputImage >::ImageDimension] [protected]

The weights used to scale derivatives during processing Definition at line 423 of file itkVectorGradientMagnitudeImageFilter.h.

template<typename TInputImage, typename TRealType = float, typename TOutputImage = Image< TRealType, ::itk::GetImageDimension<TInputImage>::ImageDimension >>

TRealType itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage >::m_SqrtComponentWeights[itk::GetVectorDimension< InputPixelType >::VectorDimension] [protected]

Definition at line 429 of file itkVectorGradientMagnitudeImageFilter.h.

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

itkVectorGradientMagnitudeImageFilter.h

Generated at Sun Apr 1 02:58:12 2007 for ITK by

itk::VectorGradientMagnitudeImageFilter< TInputImage, TRealType, TOutputImage > Class Template Reference [Image Gradient Filters]

Public Types

Public Member Functions

Static Public Member Functions

Protected Member Functions

Protected Attributes