#include <itkMRFImageFilter.h>
Inheritance diagram for itk::MRFImageFilter< TInputImage, TClassifiedImage >:
This object classifies pixels based on a Markov Random Field (MRF) model.This implementation uses the maximum a posteriori (MAP) estimates for modeling the MRF. The object traverses the data set and uses the model generated by the Mahalanobis distance classifier to gets the the distance between each pixel in the data set to a set of known classes, updates the distances by evaluating the influence of its neighboring pixels (based on a MRF model) and finally, classifies each pixel to the class which has the minimum distance to that pixel (taking the neighborhood influence under consideration). DoNeighborhoodOperation is the function that can be modified to achieve different falvors of MRF filters in derived classes.
The a classified initial labeled image is needed. It is important that the number of expected classes be set before calling the classifier. In our case we have used the ImageClassifer using a Gaussian model to generate the initial labels. This classifier requires the user to ensure that an appropriate membership functions be provided. See the documentation of the image classifier class for more information.
The influence of a neighborhood on a given pixel's classification (the MRF term) is computed by calculating a weighted sum of number of class labels in a three dimensional neighborhood. The basic idea of this neighborhood influence is that if a large number of neighbors of a pixel are of one class, then the current pixel is likely to be of the same class.
The dimensions of the neighborhood is same as the input image dimension and values of the weighting parameters are either specified by the user through the beta matrix parameter. The default weighting table is generated during object construction. The following table shows an example of a 3x3x3 neighborhood and the weighting values used. A 3 x 3 x 3 kernel is used where each value is a nonnegative parameter, which encourages neighbors to be of the same class. In this example, the influence of the pixels in the same slice is assigned a weight 1.7, the influence of the pixels in the same location in the previous and next slice is assigned a weight 1.5, while a weight 1.3 is assigned to the influence of the north, south, east, west and diagonal pixels in the previous and next slices.
![\[\begin{tabular}{ccc} \begin{tabular}{|c|c|c|} 1.3 & 1.3 & 1.3 \\ 1.3 & 1.5 & 1.3 \\ 1.3 & 1.3 & 1.3 \\ \end{tabular} & \begin{tabular}{|c|c|c|} 1.7 & 1.7 & 1.7 \\ 1.7 & 0 & 1.7 \\ 1.7 & 1.7 & 1.7 \\ \end{tabular} & \begin{tabular}{|c|c|c|} 1.3 & 1.3 & 1.3 \\ 1.5 & 1.5 & 1.3 \\ 1.3 & 1.3 & 1.3 \\ \end{tabular} \\ \end{tabular}\]](form_61.png)
The user needs to set the neighborhood size using the SetNeighborhoodRadius functions. The details on the semantics of a neighborhood can be found in the documentation associated with the itkNeighborhood and related objects. NOTE: The size of the neighborhood must match with the size of the neighborhood weighting parameters set by the user.
For minimization of the MRF labeling function the MinimizeFunctional virtual method is called. For our current implementation we use the the iterated conditional modes (ICM) algorithm described by Besag in the paper ``On the Statistical Analysis of Dirty Pictures'' in J. Royal Stat. Soc. B, Vol. 48, 1986.
In each iteration, the algorithm visits each pixel in turn and determines whether to update its classification by computing the influence of the classification of the pixel's neighbors and of the intensity data. On each iteration after the first, we reexamine the classification of a pixel only if the classification of some of its neighbors has changed in the previous iteration. The pixels' classification is updated using a synchronous scheme (iteration by iteration) until the error reaches less than the threshold or the number of iteration exceed the maximum set number of iterations. Note: The current implementation supports betaMatrix default weight for two and three dimensional images only. The default for higher dimension is set to unity. This should be over ridded by custom weights after filter initialization.
Classifier
Definition at line 131 of file itkMRFImageFilter.h.
| typedef ImageClassifierBase<TInputImage,TClassifiedImage> itk::MRFImageFilter< TInputImage, TClassifiedImage >::ClassifierType |
Type definitions for classifier to be used for the MRF lavbelling.
Reimplemented in itk::RGBGibbsPriorFilter< TInputImage, TClassifiedImage >.
Definition at line 201 of file itkMRFImageFilter.h.
| typedef SmartPointer<const Self> itk::MRFImageFilter< TInputImage, TClassifiedImage >::ConstPointer |
Reimplemented from itk::ImageToImageFilter< TInputImage, TClassifiedImage >.
Reimplemented in itk::RGBGibbsPriorFilter< TInputImage, TClassifiedImage >.
Definition at line 139 of file itkMRFImageFilter.h.
typedef DataObject::Pointer itk::ImageSource< TClassifiedImage >::DataObjectPointer [inherited] |
Smart Pointer type to a DataObject.
Reimplemented from itk::ProcessObject.
Definition at line 62 of file itkImageSource.h.
typedef std::vector<DataObjectPointer> itk::ProcessObject::DataObjectPointerArray [inherited] |
STL Array of SmartPointers to DataObjects
Definition at line 103 of file itkProcessObject.h.
typedef DataObjectPointerArray::size_type itk::ProcessObject::DataObjectPointerArraySizeType [inherited] |
Size type of an std::vector
Definition at line 112 of file itkProcessObject.h.
| typedef LabelledImageIndexType::IndexValueType itk::MRFImageFilter< TInputImage, TClassifiedImage >::IndexValueType |
Reimplemented in itk::RGBGibbsPriorFilter< TInputImage, TClassifiedImage >.
Definition at line 187 of file itkMRFImageFilter.h.
| typedef TInputImage::ConstPointer itk::MRFImageFilter< TInputImage, TClassifiedImage >::InputImageConstPointer |
Reimplemented from itk::ImageToImageFilter< TInputImage, TClassifiedImage >.
Reimplemented in itk::RGBGibbsPriorFilter< TInputImage, TClassifiedImage >.
Definition at line 151 of file itkMRFImageFilter.h.
| typedef InputImageFaceListType::iterator itk::MRFImageFilter< TInputImage, TClassifiedImage >::InputImageFaceListIterator |
Definition at line 223 of file itkMRFImageFilter.h.
| typedef InputImageFacesCalculator::FaceListType itk::MRFImageFilter< TInputImage, TClassifiedImage >::InputImageFaceListType |
Definition at line 220 of file itkMRFImageFilter.h.
| typedef NeighborhoodAlgorithm::ImageBoundaryFacesCalculator< TInputImage > itk::MRFImageFilter< TInputImage, TClassifiedImage >::InputImageFacesCalculator |
Definition at line 217 of file itkMRFImageFilter.h.
| typedef ConstNeighborhoodIterator< TInputImage > itk::MRFImageFilter< TInputImage, TClassifiedImage >::InputImageNeighborhoodIterator |
Input image neighborhood iterator and kernel size typedef
Definition at line 211 of file itkMRFImageFilter.h.
| typedef InputImageNeighborhoodIterator::RadiusType itk::MRFImageFilter< TInputImage, TClassifiedImage >::InputImageNeighborhoodRadiusType |
Definition at line 214 of file itkMRFImageFilter.h.
| typedef TInputImage::PixelType itk::MRFImageFilter< TInputImage, TClassifiedImage >::InputImagePixelType |
Type definition for the input image pixel type.
Reimplemented from itk::ImageToImageFilter< TInputImage, TClassifiedImage >.
Reimplemented in itk::RGBGibbsPriorFilter< TInputImage, TClassifiedImage >.
Definition at line 154 of file itkMRFImageFilter.h.
| typedef TInputImage::Pointer itk::MRFImageFilter< TInputImage, TClassifiedImage >::InputImagePointer |
Reimplemented from itk::ImageToImageFilter< TInputImage, TClassifiedImage >.
Reimplemented in itk::RGBGibbsPriorFilter< TInputImage, TClassifiedImage >.
Definition at line 150 of file itkMRFImageFilter.h.
| typedef ImageRegionConstIterator<TInputImage> itk::MRFImageFilter< TInputImage, TClassifiedImage >::InputImageRegionConstIterator |
Reimplemented in itk::RGBGibbsPriorFilter< TInputImage, TClassifiedImage >.
Definition at line 161 of file itkMRFImageFilter.h.
| typedef ImageRegionIterator<TInputImage> itk::MRFImageFilter< TInputImage, TClassifiedImage >::InputImageRegionIterator |
Type definition for the input image region iterator
Reimplemented in itk::RGBGibbsPriorFilter< TInputImage, TClassifiedImage >.
Definition at line 160 of file itkMRFImageFilter.h.
| typedef TInputImage::RegionType itk::MRFImageFilter< TInputImage, TClassifiedImage >::InputImageRegionType |
Type definition for the input image region type.
Reimplemented from itk::ImageToImageFilter< TInputImage, TClassifiedImage >.
Definition at line 157 of file itkMRFImageFilter.h.
| typedef TInputImage itk::MRFImageFilter< TInputImage, TClassifiedImage >::InputImageType |
Type definition for the input image.
Reimplemented from itk::ImageToImageFilter< TInputImage, TClassifiedImage >.
Reimplemented in itk::RGBGibbsPriorFilter< TInputImage, TClassifiedImage >.
Definition at line 146 of file itkMRFImageFilter.h.
typedef ImageToImageFilterDetail::ImageRegionCopier<itkGetStaticConstMacro(OutputImageDimension), itkGetStaticConstMacro(InputImageDimension)> itk::ImageToImageFilter< TInputImage , TClassifiedImage >::InputToOutputRegionCopierType [protected, inherited] |
Typedef for the region copier function object that converts an input region to an output region.
Definition at line 164 of file itkImageToImageFilter.h.
| typedef LabelledImageFaceListType::iterator itk::MRFImageFilter< TInputImage, TClassifiedImage >::LabelledImageFaceListIterator |
Definition at line 239 of file itkMRFImageFilter.h.
| typedef LabelledImageFacesCalculator::FaceListType itk::MRFImageFilter< TInputImage, TClassifiedImage >::LabelledImageFaceListType |
Definition at line 236 of file itkMRFImageFilter.h.
| typedef NeighborhoodAlgorithm::ImageBoundaryFacesCalculator< TClassifiedImage > itk::MRFImageFilter< TInputImage, TClassifiedImage >::LabelledImageFacesCalculator |
Definition at line 233 of file itkMRFImageFilter.h.
| typedef TClassifiedImage::IndexType itk::MRFImageFilter< TInputImage, TClassifiedImage >::LabelledImageIndexType |
Type definition for the classified image index type.
Reimplemented in itk::RGBGibbsPriorFilter< TInputImage, TClassifiedImage >.
Definition at line 186 of file itkMRFImageFilter.h.
| typedef NeighborhoodIterator< TClassifiedImage > itk::MRFImageFilter< TInputImage, TClassifiedImage >::LabelledImageNeighborhoodIterator |
Labelled image neighborhood interator typedef
Definition at line 227 of file itkMRFImageFilter.h.
| typedef LabelledImageNeighborhoodIterator::RadiusType itk::MRFImageFilter< TInputImage, TClassifiedImage >::LabelledImageNeighborhoodRadiusType |
Definition at line 230 of file itkMRFImageFilter.h.
| typedef TClassifiedImage::OffsetType itk::MRFImageFilter< TInputImage, TClassifiedImage >::LabelledImageOffsetType |
Type definition for the classified image offset type.
Definition at line 190 of file itkMRFImageFilter.h.
| typedef TClassifiedImage::PixelType itk::MRFImageFilter< TInputImage, TClassifiedImage >::LabelledImagePixelType |
Type definitions for the classified image pixel type. It has to be the same type as the training image.
Reimplemented in itk::RGBGibbsPriorFilter< TInputImage, TClassifiedImage >.
Definition at line 179 of file itkMRFImageFilter.h.
| typedef TClassifiedImage::Pointer itk::MRFImageFilter< TInputImage, TClassifiedImage >::LabelledImagePointer |
Type definitions for the labelled image. It is derived from the training image.
Definition at line 175 of file itkMRFImageFilter.h.
| typedef ImageRegionIterator<TClassifiedImage> itk::MRFImageFilter< TInputImage, TClassifiedImage >::LabelledImageRegionIterator |
Type definition for the input image region iterator
Reimplemented in itk::RGBGibbsPriorFilter< TInputImage, TClassifiedImage >.
Definition at line 194 of file itkMRFImageFilter.h.
| typedef TClassifiedImage::RegionType itk::MRFImageFilter< TInputImage, TClassifiedImage >::LabelledImageRegionType |
Type definitions for the classified image pixel type. It has to be the same type as the training image.
Definition at line 183 of file itkMRFImageFilter.h.
typedef ImageRegionIterator< LabelStatusImageType > itk::MRFImageFilter< TInputImage, TClassifiedImage >::LabelStatusImageIterator [protected] |
Definition at line 350 of file itkMRFImageFilter.h.
typedef NeighborhoodIterator< LabelStatusImageType > itk::MRFImageFilter< TInputImage, TClassifiedImage >::LabelStatusImageNeighborhoodIterator [protected] |
Labelled status image neighborhood interator typedef
Definition at line 354 of file itkMRFImageFilter.h.
typedef LabelStatusImageType::Pointer itk::MRFImageFilter< TInputImage, TClassifiedImage >::LabelStatusImagePointer [protected] |
Definition at line 348 of file itkMRFImageFilter.h.
typedef Image<int,itkGetStaticConstMacro(InputImageDimension) > itk::MRFImageFilter< TInputImage, TClassifiedImage >::LabelStatusImageType [protected] |
Definition at line 345 of file itkMRFImageFilter.h.
typedef LabelStatusImageType::IndexType itk::MRFImageFilter< TInputImage, TClassifiedImage >::LabelStatusIndexType [protected] |
Definition at line 346 of file itkMRFImageFilter.h.
typedef LabelStatusImageType::RegionType itk::MRFImageFilter< TInputImage, TClassifiedImage >::LabelStatusRegionType [protected] |
Definition at line 347 of file itkMRFImageFilter.h.
| typedef TInputImage::SizeType itk::MRFImageFilter< TInputImage, TClassifiedImage >::NeighborhoodRadiusType |
Radius typedef support.
Definition at line 207 of file itkMRFImageFilter.h.
typedef Superclass::OutputImagePixelType itk::ImageToImageFilter< TInputImage , TClassifiedImage >::OutputImagePixelType [inherited] |
Reimplemented from itk::ImageSource< TClassifiedImage >.
Definition at line 79 of file itkImageToImageFilter.h.
| typedef Superclass::OutputImagePointer itk::MRFImageFilter< TInputImage, TClassifiedImage >::OutputImagePointer |
Reimplemented from itk::ImageSource< TClassifiedImage >.
Definition at line 140 of file itkMRFImageFilter.h.
typedef Superclass::OutputImageRegionType itk::ImageToImageFilter< TInputImage , TClassifiedImage >::OutputImageRegionType [inherited] |
Superclass typedefs.
Reimplemented from itk::ImageSource< TClassifiedImage >.
Definition at line 75 of file itkImageToImageFilter.h.
typedef TClassifiedImage itk::ImageSource< TClassifiedImage >::OutputImageType [inherited] |
Some convenient typedefs.
Definition at line 65 of file itkImageSource.h.
typedef ImageToImageFilterDetail::ImageRegionCopier<itkGetStaticConstMacro(InputImageDimension), itkGetStaticConstMacro(OutputImageDimension)> itk::ImageToImageFilter< TInputImage , TClassifiedImage >::OutputToInputRegionCopierType [protected, inherited] |
Typedef for the region copier function object that converts an output region to an input region.
Definition at line 169 of file itkImageToImageFilter.h.
| typedef SmartPointer<Self> itk::MRFImageFilter< TInputImage, TClassifiedImage >::Pointer |
Reimplemented from itk::ImageToImageFilter< TInputImage, TClassifiedImage >.
Reimplemented in itk::RGBGibbsPriorFilter< TInputImage, TClassifiedImage >.
Definition at line 138 of file itkMRFImageFilter.h.
| typedef MRFImageFilter itk::MRFImageFilter< TInputImage, TClassifiedImage >::Self |
Standard class typedefs.
Reimplemented from itk::ImageToImageFilter< TInputImage, TClassifiedImage >.
Reimplemented in itk::RGBGibbsPriorFilter< TInputImage, TClassifiedImage >.
Definition at line 136 of file itkMRFImageFilter.h.
| typedef TInputImage::SizeType itk::MRFImageFilter< TInputImage, TClassifiedImage >::SizeType |
Size and value typedef support.
Definition at line 204 of file itkMRFImageFilter.h.
| typedef ImageToImageFilter<TInputImage,TClassifiedImage> itk::MRFImageFilter< TInputImage, TClassifiedImage >::Superclass |
Reimplemented from itk::ImageToImageFilter< TInputImage, TClassifiedImage >.
Reimplemented in itk::RGBGibbsPriorFilter< TInputImage, TClassifiedImage >.
Definition at line 137 of file itkMRFImageFilter.h.
| typedef TClassifiedImage::PixelType itk::MRFImageFilter< TInputImage, TClassifiedImage >::TrainingImagePixelType |
Type definitions for the training image pixel type.
Definition at line 171 of file itkMRFImageFilter.h.
| typedef TClassifiedImage::Pointer itk::MRFImageFilter< TInputImage, TClassifiedImage >::TrainingImagePointer |
Type definitions for the training image.
Definition at line 168 of file itkMRFImageFilter.h.
| enum itk::MRFImageFilter::StopConditionType |
Definition at line 300 of file itkMRFImageFilter.h.
| itk::MRFImageFilter< TInputImage, TClassifiedImage >::MRFImageFilter | ( | ) | [protected] |
| itk::MRFImageFilter< TInputImage, TClassifiedImage >::~MRFImageFilter | ( | ) | [protected] |
| virtual void itk::ProcessObject::AbortGenerateDataOff | ( | ) | [virtual, inherited] |
| virtual void itk::ProcessObject::AbortGenerateDataOn | ( | ) | [virtual, inherited] |
Turn on and off the AbortGenerateData flag.
| virtual void itk::ProcessObject::AddInput | ( | DataObject * | input | ) | [protected, virtual, inherited] |
| unsigned long itk::Object::AddObserver | ( | const EventObject & | event, | |
| Command * | ||||
| ) | const [inherited] |
| unsigned long itk::Object::AddObserver | ( | const EventObject & | event, | |
| Command * | ||||
| ) | [inherited] |
Allow people to add/remove/invoke observers (callbacks) to any ITK object. This is an implementation of the subject/observer design pattern. An observer is added by specifying an event to respond to and an itk::Command to execute. It returns an unsigned long tag which can be used later to remove the event or retrieve the command. The memory for the Command becomes the responsibility of this object, so don't pass the same instance of a command to two different objects
| virtual void itk::ProcessObject::AddOutput | ( | DataObject * | output | ) | [protected, virtual, inherited] |
| virtual void itk::ImageSource< TClassifiedImage >::AfterThreadedGenerateData | ( | void |