Blurs an image while preserving edges. More...

#include <itkBilateralImageFilter.h>

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

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

Public Types
typedef FixedArray< double, itkGetStaticConstMacro(ImageDimension) >	ArrayType
typedef SmartPointer< const Self >	ConstPointer
typedef Image< double, itkGetStaticConstMacro(ImageDimension) >	GaussianImageType
typedef TInputImage	InputImageType
typedef TInputImage::InternalPixelType	InputInternalPixelType
typedef TInputImage::PixelType	InputPixelType
typedef KernelType::ConstIterator	KernelConstIteratorType
typedef KernelType::Iterator	KernelIteratorType
typedef Neighborhood< double, itkGetStaticConstMacro(ImageDimension) >	KernelType
typedef ConstNeighborhoodIterator < TInputImage >	NeighborhoodIteratorType
typedef Superclass::OutputImageRegionType	OutputImageRegionType
typedef TOutputImage	OutputImageType
typedef TOutputImage::InternalPixelType	OutputInternalPixelType
typedef NumericTraits < OutputPixelType >::RealType	OutputPixelRealType
typedef TOutputImage::PixelType	OutputPixelType
typedef SmartPointer< Self >	Pointer
typedef BilateralImageFilter	Self
typedef KernelType::SizeType	SizeType
typedef KernelType::SizeValueType	SizeValueType
typedef ImageToImageFilter < TInputImage, TOutputImage >	Superclass
Public Member Functions
virtual ::itk::LightObject::Pointer	CreateAnother (void) const
virtual const char *	GetNameOfClass () const
virtual const SizeType &	GetRadius ()
void	SetDomainSigma (const double v)
void	SetRadius (const SizeValueType)
virtual void	SetRadius (SizeType _arg)
	typedef (Concept::HasNumericTraits< OutputPixelType >) OutputHasNumericTraitsCheck

virtual void	SetDomainSigma (ArrayType _arg)
virtual const ArrayType	GetDomainSigma () const
virtual void	SetRangeSigma (double _arg)
virtual double	GetRangeSigma () const
virtual unsigned int	GetFilterDimensionality () const
virtual void	SetFilterDimensionality (unsigned int _arg)

virtual void	AutomaticKernelSizeOn ()
virtual void	AutomaticKernelSizeOff ()
virtual bool	GetAutomaticKernelSize () const
virtual void	SetAutomaticKernelSize (bool _arg)

virtual void	SetNumberOfRangeGaussianSamples (unsigned long _arg)
virtual unsigned long	GetNumberOfRangeGaussianSamples () const
Static Public Member Functions
static Pointer	New ()
Static Public Attributes
static const unsigned int	ImageDimension = TOutputImage::ImageDimension
Protected Member Functions
void	BeforeThreadedGenerateData ()
virtual void	GenerateInputRequestedRegion () throw ( InvalidRequestedRegionError )
void	PrintSelf (std::ostream &os, Indent indent) const
void	ThreadedGenerateData (const OutputImageRegionType &outputRegionForThread, ThreadIdType threadId)
virtual	~BilateralImageFilter ()

	BilateralImageFilter ()
Private Member Functions
	BilateralImageFilter (const Self &)
void	operator= (const Self &)
Private Attributes
bool	m_AutomaticKernelSize
double	m_DomainMu
ArrayType	m_DomainSigma
double	m_DynamicRange
double	m_DynamicRangeUsed
unsigned int	m_FilterDimensionality
KernelType	m_GaussianKernel
unsigned long	m_NumberOfRangeGaussianSamples
SizeType	m_Radius
std::vector< double >	m_RangeGaussianTable
double	m_RangeMu
double	m_RangeSigma

Detailed Description

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

Blurs an image while preserving edges.

This filter uses bilateral filtering to blur an image using both domain and range "neighborhoods". Pixels that are close to a pixel in the image domain and similar to a pixel in the image range are used to calculate the filtered value. Two gaussian kernels (one in the image domain and one in the image range) are used to smooth the image. The result is an image that is smoothed in homogeneous regions yet has edges preserved. The result is similar to anisotropic diffusion but the implementation in non-iterative. Another benefit to bilateral filtering is that any distance metric can be used for kernel smoothing the image range. Hence, color images can be smoothed as vector images, using the CIE distances between intensity values as the similarity metric (the Gaussian kernel for the image domain is evaluated using CIE distances). A separate version of this filter will be designed for color and vector images.

Bilateral filtering is capable of reducing the noise in an image by an order of magnitude while maintaining edges.

The bilateral operator used here was described by Tomasi and Manduchi (Bilateral Filtering for Gray and ColorImages. IEEE ICCV. 1998.)

See also:: GaussianOperator; RecursiveGaussianImageFilter; DiscreteGaussianImageFilter; AnisotropicDiffusionImageFilter; Image; Neighborhood; NeighborhoodOperator

Todo:

Support color images

Support vector images

Wiki Examples:

All Examples

Bilateral filter an image

Definition at line 75 of file itkBilateralImageFilter.h.