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

itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 > Class Template Reference

Measures the similarity between the set of non-zero pixels of two images. More...

#include <itkSimilarityIndexImageFilter.h>

Inheritance diagram for itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >:

Inheritance graph
[legend]
Collaboration diagram for itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >:

Collaboration graph
[legend]
List of all members.

Public Types

typedef SimilarityIndexImageFilter Self
typedef ImageToImageFilter<
TInputImage1, TInputImage1 > 		Superclass
typedef SmartPointer< Self > Pointer
typedef SmartPointer< const
Self > 		ConstPointer
typedef TInputImage1 InputImage1Type
typedef TInputImage2 InputImage2Type
typedef TInputImage1::Pointer InputImage1Pointer
typedef TInputImage2::Pointer InputImage2Pointer
typedef TInputImage1::ConstPointer InputImage1ConstPointer
typedef TInputImage2::ConstPointer InputImage2ConstPointer
typedef TInputImage1::RegionType RegionType
typedef TInputImage1::SizeType SizeType
typedef TInputImage1::IndexType IndexType
typedef TInputImage1::PixelType InputImage1PixelType
typedef TInputImage2::PixelType InputImage2PixelType
typedef NumericTraits< InputImage1PixelType
>::RealType 		RealType

Public Member Functions

virtual const char * GetNameOfClass () const
 itkStaticConstMacro (ImageDimension, unsigned int, TInputImage1::ImageDimension)
void SetInput1 (const InputImage1Type *image)
void SetInput2 (const InputImage2Type *image)
const InputImage1Type * GetInput1 (void)
const InputImage2Type * GetInput2 (void)
virtual RealType GetSimilarityIndex ()

Static Public Member Functions

Pointer New ()

Protected Member Functions

 SimilarityIndexImageFilter ()
 ~SimilarityIndexImageFilter ()
void PrintSelf (std::ostream &os, Indent indent) const
void AllocateOutputs ()
void BeforeThreadedGenerateData ()
void AfterThreadedGenerateData ()
void ThreadedGenerateData (const RegionType &outputRegionForThread, int threadId)
void GenerateInputRequestedRegion ()
void EnlargeOutputRequestedRegion (DataObject *data)

Detailed Description

template<class TInputImage1, class TInputImage2>
class itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >

Measures the similarity between the set of non-zero pixels of two images.

SimilarityIndexImageFilter measures the similarity between the set non-zero pixels of two images using the following formula:

\[ S = \frac{2 | A \cap B |}{|A| + |B|} \]

where $A$ and $B$ are respectively the set of non-zero pixels in the first and second input images. Operator $|\cdot|$ represents the size of a set and $\cap$ represents the intersection of two sets.

The measure is derived from a reliability measure known as the kappa statistic. $S$ is sensitive to both differences in size and in location and have been in the literature for comparing two segmentation masks. For more information see: "Morphometric Analysis of White Matter Lesions in MR Images: Method and Validation", A. P. Zijdenbos, B. M. Dawant, R. A. Margolin and A. C. Palmer, IEEE Trans. on Medical Imaging, 13(4) pp 716-724,1994

This filter requires the largest possible region of the first image and the same corresponding region in the second image. It behaves as filter with two input and one output. Thus it can be inserted in a pipeline with other filters. The filter passes the first input through unmodified.

This filter is templated over the two input image type. It assume both image have the same number of dimensions.

Definition at line 58 of file itkSimilarityIndexImageFilter.h.

Member Typedef Documentation

template<class TInputImage1, class TInputImage2>
typedef SmartPointer<const Self> itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::ConstPointer
 

Reimplemented from itk::ImageToImageFilter< TInputImage1, TInputImage1 >.

Definition at line 66 of file itkSimilarityIndexImageFilter.h.

template<class TInputImage1, class TInputImage2>
typedef TInputImage1::IndexType itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::IndexType
 

Definition at line 84 of file itkSimilarityIndexImageFilter.h.

template<class TInputImage1, class TInputImage2>
typedef TInputImage1::ConstPointer itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::InputImage1ConstPointer
 

Definition at line 79 of file itkSimilarityIndexImageFilter.h.

template<class TInputImage1, class TInputImage2>
typedef TInputImage1::PixelType itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::InputImage1PixelType
 

Definition at line 86 of file itkSimilarityIndexImageFilter.h.

template<class TInputImage1, class TInputImage2>
typedef TInputImage1::Pointer itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::InputImage1Pointer
 

Definition at line 77 of file itkSimilarityIndexImageFilter.h.

template<class TInputImage1, class TInputImage2>
typedef TInputImage1 itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::InputImage1Type
 

Image related typedefs.

Definition at line 75 of file itkSimilarityIndexImageFilter.h.

Referenced by itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::GetInput1(), and itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::SetInput1().

template<class TInputImage1, class TInputImage2>
typedef TInputImage2::ConstPointer itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::InputImage2ConstPointer
 

Definition at line 80 of file itkSimilarityIndexImageFilter.h.

template<class TInputImage1, class TInputImage2>
typedef TInputImage2::PixelType itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::InputImage2PixelType
 

Definition at line 87 of file itkSimilarityIndexImageFilter.h.

template<class TInputImage1, class TInputImage2>
typedef TInputImage2::Pointer itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::InputImage2Pointer
 

Definition at line 78 of file itkSimilarityIndexImageFilter.h.

template<class TInputImage1, class TInputImage2>
typedef TInputImage2 itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::InputImage2Type
 

Definition at line 76 of file itkSimilarityIndexImageFilter.h.

template<class TInputImage1, class TInputImage2>
typedef SmartPointer<Self> itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::Pointer
 

Reimplemented from itk::ImageToImageFilter< TInputImage1, TInputImage1 >.

Definition at line 65 of file itkSimilarityIndexImageFilter.h.

template<class TInputImage1, class TInputImage2>
typedef NumericTraits<InputImage1PixelType>::RealType itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::RealType
 

Type to use form computations.

Definition at line 94 of file itkSimilarityIndexImageFilter.h.

template<class TInputImage1, class TInputImage2>
typedef TInputImage1::RegionType itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::RegionType
 

Definition at line 82 of file itkSimilarityIndexImageFilter.h.

template<class TInputImage1, class TInputImage2>
typedef SimilarityIndexImageFilter itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::Self
 

Standard Self typedef

Reimplemented from itk::ImageToImageFilter< TInputImage1, TInputImage1 >.

Definition at line 63 of file itkSimilarityIndexImageFilter.h.

template<class TInputImage1, class TInputImage2>
typedef TInputImage1::SizeType itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::SizeType
 

Definition at line 83 of file itkSimilarityIndexImageFilter.h.

template<class TInputImage1, class TInputImage2>
typedef ImageToImageFilter<TInputImage1,TInputImage1> itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::Superclass
 

Reimplemented from itk::ImageToImageFilter< TInputImage1, TInputImage1 >.

Definition at line 64 of file itkSimilarityIndexImageFilter.h.

Constructor & Destructor Documentation

template<class TInputImage1, class TInputImage2>
itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::SimilarityIndexImageFilter (   )  [protected]
 

template<class TInputImage1, class TInputImage2>
itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::~SimilarityIndexImageFilter (   )  [inline, protected]
 

Definition at line 115 of file itkSimilarityIndexImageFilter.h.

Member Function Documentation

template<class TInputImage1, class TInputImage2>
void itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::AfterThreadedGenerateData (   )  [protected, virtual]
 

Do final mean and variance computation from data accumulated in threads.

Reimplemented from itk::ImageSource< TInputImage1 >.

template<class TInputImage1, class TInputImage2>
void itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::AllocateOutputs (   )  [protected, virtual]
 

Pass the input through unmodified. Do this by Grafting in the AllocateOutputs method.

Reimplemented from itk::ImageSource< TInputImage1 >.

template<class TInputImage1, class TInputImage2>
void itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::BeforeThreadedGenerateData (   )  [protected, virtual]
 

Initialize some accumulators before the threads run.

Reimplemented from itk::ImageSource< TInputImage1 >.

template<class TInputImage1, class TInputImage2>
void itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::EnlargeOutputRequestedRegion (  DataObject *  data  )  [protected, virtual]
 

Give the process object a chance to indictate that it will produce more output than it was requested to produce. For example, many imaging filters must compute the entire output at once or can only produce output in complete slices. Such filters cannot handle smaller requested regions. These filters must provide an implementation of this method, setting the output requested region to the size they will produce. By default, a process object does not modify the size of the output requested region.

Reimplemented from itk::ProcessObject.

template<class TInputImage1, class TInputImage2>
void itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::GenerateInputRequestedRegion (   )  [protected, virtual]
 

What is the input requested region that is required to produce the output requested region? The base assumption for image processing filters is that the input requested region can be set to match the output requested region. If a filter requires more input (for instance a filter that uses neighborhoods needs more input than output to avoid introducing artificial boundary conditions) or less input (for instance a magnify filter) will have to override this method. In doing so, it should call its superclass' implementation as its first step. Note that imaging filters operate differently than the classes to this point in the class hierachy. Up till now, the base assumption has been that the largest possible region will be requested of the input.

This implementation of GenerateInputRequestedRegion() only processes the inputs that are a subclass of the ImageBase<InputImageDimension>. If an input is another type of DataObject (including an Image of a different dimension), they are skipped by this method. The subclasses of ImageToImageFilter are responsible for providing an implementation of GenerateInputRequestedRegion() when there are multiple inputs of different types.

See also:
ProcessObject::GenerateInputRequestedRegion(), ImageSource::GenerateInputRequestedRegion()

Reimplemented from itk::ImageToImageFilter< TInputImage1, TInputImage1 >.

template<class TInputImage1, class TInputImage2>
const InputImage1Type* itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::GetInput1 (  void   )  [inline]
 

Get the first input.

Definition at line 104 of file itkSimilarityIndexImageFilter.h.

References itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::InputImage1Type.

template<class TInputImage1, class TInputImage2>
const InputImage2Type* itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::GetInput2 (  void   ) 
 

Get the secong input.

template<class TInputImage1, class TInputImage2>
virtual const char* itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::GetNameOfClass (   )  const [virtual]
 

Runtime information support.

Reimplemented from itk::ImageToImageFilter< TInputImage1, TInputImage1 >.

template<class TInputImage1, class TInputImage2>
virtual RealType itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::GetSimilarityIndex (   )  [virtual]
 

Return the computed similarity index.

template<class TInputImage1, class TInputImage2>
itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::itkStaticConstMacro (  ImageDimension  ,
unsigned  int,
TInputImage1::ImageDimension 
) 
 

Image related typedefs.

template<class TInputImage1, class TInputImage2>
Pointer itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::New (   )  [static]
 

Method for creation through the object factory.

Reimplemented from itk::Object.

template<class TInputImage1, class TInputImage2>
void itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::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< TInputImage1, TInputImage1 >.

template<class TInputImage1, class TInputImage2>
void itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::SetInput1 (  const InputImage1Type *  image  )  [inline]
 

Set the first input.

Definition at line 97 of file itkSimilarityIndexImageFilter.h.

References itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::InputImage1Type.

template<class TInputImage1, class TInputImage2>
void itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::SetInput2 (  const InputImage2Type *  image  ) 
 

Set the second input.

template<class TInputImage1, class TInputImage2>
void itk::SimilarityIndexImageFilter< TInputImage1, TInputImage2 >::ThreadedGenerateData (  const RegionType &  outputRegionForThread,
int  threadId
)  [protected]
 

Multi-thread version GenerateData.

The documentation for this class was generated from the following file:
Generated at Thu May 25 02:21:02 2006 for ITK by doxygen 1.3.5 written by Dimitri van Heesch, © 1997-2000