itk::ImageGaussianModelEstimator< TInputImage, TMembershipFunction, TTrainingImage > Class Template Reference
[Pixel Classification Filters]

Base class for ImageGaussianModelEstimator object. More...

#include <itkImageGaussianModelEstimator.h>

Inheritance diagram for itk::ImageGaussianModelEstimator:

[legend]Collaboration diagram for itk::ImageGaussianModelEstimator< TInputImage, TMembershipFunction, TTrainingImage >:

[legend]List of all members.

Public Types
typedef ImageGaussianModelEstimator	Self
typedef ImageModelEstimatorBase< TInputImage, TMembershipFunction >	Superclass
typedef SmartPointer< Self >	Pointer
typedef SmartPointer< const Self >	ConstPointer
typedef TInputImage::Pointer	InputImagePointer
typedef TTrainingImage::Pointer	TrainingImagePointer
typedef TInputImage::PixelType	InputImagePixelType
typedef TTrainingImage::PixelType	TrainingImagePixelType
typedef ImageRegionIterator< TInputImage >	InputImageIterator
typedef ImageRegionIterator< TTrainingImage >	TrainingImageIterator
typedef TMembershipFunction::Pointer	MembershipFunctionPointer
Public Methods
virtual const char *	GetClassName () const
virtual void	SetTrainingImage (TrainingImagePointer _arg)
virtual TrainingImagePointer	GetTrainingImage ()
Static Public Methods
Pointer	New ()
Protected Methods
	ImageGaussianModelEstimator ()
	~ImageGaussianModelEstimator ()
virtual void	PrintSelf (std::ostream &os, Indent indent) const
void	GenerateData ()

---

Detailed Description

template<class TInputImage, class TMembershipFunction, class TTrainingImage>
class itk::ImageGaussianModelEstimator< TInputImage, TMembershipFunction, TTrainingImage >

Base class for ImageGaussianModelEstimator object.

itkImageGaussianModelEstimator generated the gaussian model for given tissue types (or class types) in an input training set. training data set for segmentation. The training data set is typically provided as a set of labelled/classified data set by the user. A gaussian model is generated for each label present in the training data set. from the training data set.

The user should ensure that both the input and training images are of the same size. The input data consists of the raw data and the training data has class labels associated with each pixel. However, only a subset of the data need to be labelled. Unlabelled data could be represented by a non zero, non positive number. The training data are anaysed for identifying the classes. Any non zero, non negative value is considered a valid label. It is important that the maximum value of the training label be equal to N, where N is the number of classes represented by the maximum label value in the training data set. The pixels corresponding to each training label is parsed and the mean and covariance is calculated for each class.

This object supports data handling of multiband images. The object accepts the input image in vector format only, where each pixel is a vector and each element of the vector corresponds to an entry from 1 particular band of a multiband dataset. A single band image is treated as a vector image with a single element for every vector. The classified image is treated as a single band scalar image.

This function is templated over the type of input and output images. In addition, a third parameter for the MembershipFunction needs to be specified. In this case a Membership function that store Gaussian models needs to be specified.

The function EstimateModels() calculated the various models, creates the membership function objects and populates them.

Definition at line 79 of file itkImageGaussianModelEstimator.h.

---

Member Typedef Documentation

template<class TInputImage, class TMembershipFunction, class TTrainingImage> typedef SmartPointer<const Self> itk::ImageGaussianModelEstimator< TInputImage, TMembershipFunction, TTrainingImage >::ConstPointer

Reimplemented from itk::ImageModelEstimatorBase< TInputImage, TMembershipFunction >. Definition at line 88 of file itkImageGaussianModelEstimator.h.

template<class TInputImage, class TMembershipFunction, class TTrainingImage> typedef ImageRegionIterator< TInputImage > itk::ImageGaussianModelEstimator< TInputImage, TMembershipFunction, TTrainingImage >::InputImageIterator

Type definitions for the iterators for the input and training images. Definition at line 112 of file itkImageGaussianModelEstimator.h.

template<class TInputImage, class TMembershipFunction, class TTrainingImage> typedef TInputImage::PixelType itk::ImageGaussianModelEstimator< TInputImage, TMembershipFunction, TTrainingImage >::InputImagePixelType

Type definition for the vector associated with input image pixel type. Definition at line 104 of file itkImageGaussianModelEstimator.h.

template<class TInputImage, class TMembershipFunction, class TTrainingImage> typedef TInputImage::Pointer itk::ImageGaussianModelEstimator< TInputImage, TMembershipFunction, TTrainingImage >::InputImagePointer

Type definition for the input image. Reimplemented from itk::ImageModelEstimatorBase< TInputImage, TMembershipFunction >. Definition at line 97 of file itkImageGaussianModelEstimator.h.

template<class TInputImage, class TMembershipFunction, class TTrainingImage> typedef TMembershipFunction::Pointer itk::ImageGaussianModelEstimator< TInputImage, TMembershipFunction, TTrainingImage >::MembershipFunctionPointer

Type definitions for the membership function . Reimplemented from itk::ImageModelEstimatorBase< TInputImage, TMembershipFunction >. Definition at line 117 of file itkImageGaussianModelEstimator.h.

template<class TInputImage, class TMembershipFunction, class TTrainingImage> typedef SmartPointer<Self> itk::ImageGaussianModelEstimator< TInputImage, TMembershipFunction, TTrainingImage >::Pointer

Reimplemented from itk::ImageModelEstimatorBase< TInputImage, TMembershipFunction >. Definition at line 87 of file itkImageGaussianModelEstimator.h.

template<class TInputImage, class TMembershipFunction, class TTrainingImage> typedef ImageGaussianModelEstimator itk::ImageGaussianModelEstimator< TInputImage, TMembershipFunction, TTrainingImage >::Self

Standard class typedefs. Reimplemented from itk::ImageModelEstimatorBase< TInputImage, TMembershipFunction >. Definition at line 84 of file itkImageGaussianModelEstimator.h.

template<class TInputImage, class TMembershipFunction, class TTrainingImage> typedef ImageModelEstimatorBase<TInputImage,TMembershipFunction> itk::ImageGaussianModelEstimator< TInputImage, TMembershipFunction, TTrainingImage >::Superclass

Reimplemented from itk::ImageModelEstimatorBase< TInputImage, TMembershipFunction >. Definition at line 85 of file itkImageGaussianModelEstimator.h.

template<class TInputImage, class TMembershipFunction, class TTrainingImage> typedef ImageRegionIterator< TTrainingImage > itk::ImageGaussianModelEstimator< TInputImage, TMembershipFunction, TTrainingImage >::TrainingImageIterator

Definition at line 114 of file itkImageGaussianModelEstimator.h.

template<class TInputImage, class TMembershipFunction, class TTrainingImage> typedef TTrainingImage::PixelType itk::ImageGaussianModelEstimator< TInputImage, TMembershipFunction, TTrainingImage >::TrainingImagePixelType

Type definitions for the vector holding training image pixel type. Definition at line 108 of file itkImageGaussianModelEstimator.h.

template<class TInputImage, class TMembershipFunction, class TTrainingImage> typedef TTrainingImage::Pointer itk::ImageGaussianModelEstimator< TInputImage, TMembershipFunction, TTrainingImage >::TrainingImagePointer

Type definitions for the training image. Definition at line 100 of file itkImageGaussianModelEstimator.h.

---

Constructor & Destructor Documentation

template<class TInputImage, class TMembershipFunction, class TTrainingImage> itk::ImageGaussianModelEstimator< TInputImage, TMembershipFunction, TTrainingImage >::ImageGaussianModelEstimator (    )  [protected]

template<class TInputImage, class TMembershipFunction, class TTrainingImage> itk::ImageGaussianModelEstimator< TInputImage, TMembershipFunction, TTrainingImage >::~ImageGaussianModelEstimator (    )  [protected]

---

Member Function Documentation

template<class TInputImage, class TMembershipFunction, class TTrainingImage> void itk::ImageGaussianModelEstimator< TInputImage, TMembershipFunction, TTrainingImage >::GenerateData (    )  [protected, virtual]

Starts the image modelling process Reimplemented from itk::ImageModelEstimatorBase< TInputImage, TMembershipFunction >.

template<class TInputImage, class TMembershipFunction, class TTrainingImage> virtual const char* itk::ImageGaussianModelEstimator< TInputImage, TMembershipFunction, TTrainingImage >::GetClassName (    )  const [virtual]

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

template<class TInputImage, class TMembershipFunction, class TTrainingImage> virtual TrainingImagePointer itk::ImageGaussianModelEstimator< TInputImage, TMembershipFunction, TTrainingImage >::GetTrainingImage (    )  [virtual]

Get the training image.

template<class TInputImage, class TMembershipFunction, class TTrainingImage> Pointer itk::ImageGaussianModelEstimator< TInputImage, TMembershipFunction, TTrainingImage >::New (    )  [static]

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

template<class TInputImage, class TMembershipFunction, class TTrainingImage> virtual void itk::ImageGaussianModelEstimator< TInputImage, TMembershipFunction, TTrainingImage >::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::ImageModelEstimatorBase< TInputImage, TMembershipFunction >.

template<class TInputImage, class TMembershipFunction, class TTrainingImage> virtual void itk::ImageGaussianModelEstimator< TInputImage, TMembershipFunction, TTrainingImage >::SetTrainingImage (  TrainingImagePointer    _arg )  [virtual]

Set the training image.

---

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

• itkImageGaussianModelEstimator.h

---