ITK
4.3.0
Insight Segmentation and Registration Toolkit
|
#include <itkKappaStatisticImageToImageMetric.h>
Computes similarity between two binary objects to be registered.
This Class is templated over the type of the fixed and moving images to be compared. The metric here is designed for matching pixels in two images with the same exact value. Only one value can be considered (the default is 255) and can be specified with the SetForegroundValue method. In the computation of the metric, only foreground pixels are considered. The metric value is given by 2*|A&B|/(|A|+|B|), where A is the foreground region in the moving image, B is the foreground region in the fixed image, & is intersection, and |.| indicates the area of the enclosed set. The metric is described in "Morphometric Analysis of White Matter Lesions in MR Images: Method and Validation", A. P. Zijdenbos, B. M. Dawant, R. A. Margolin, A. C. Palmer.
This metric is especially useful when considering the similarity between binary images. Given the nature of binary images, a nearest neighbor interpolator is the preferred interpolator.
Metric values range from 0.0 (no foreground alignment) to 1.0 (perfect foreground alignment). When dealing with optimizers that can only minimize a metric, use the ComplementOn() method.
Definition at line 54 of file itkKappaStatisticImageToImageMetric.h.
Static Public Member Functions | |
static Pointer | New () |
Private Member Functions | |
KappaStatisticImageToImageMetric (const Self &) | |
void | operator= (const Self &) |
Private Attributes | |
bool | m_Complement |
RealType | m_ForegroundValue |
typedef SmartPointer< const Self > itk::KappaStatisticImageToImageMetric< TFixedImage, TMovingImage >::ConstPointer |
Definition at line 63 of file itkKappaStatisticImageToImageMetric.h.
typedef Superclass::DerivativeType itk::KappaStatisticImageToImageMetric< TFixedImage, TMovingImage >::DerivativeType |
Definition at line 83 of file itkKappaStatisticImageToImageMetric.h.
typedef Superclass::FixedImageConstPointer itk::KappaStatisticImageToImageMetric< TFixedImage, TMovingImage >::FixedImageConstPointer |
Definition at line 86 of file itkKappaStatisticImageToImageMetric.h.
typedef Superclass::FixedImageRegionType itk::KappaStatisticImageToImageMetric< TFixedImage, TMovingImage >::FixedImageRegionType |
Definition at line 88 of file itkKappaStatisticImageToImageMetric.h.
typedef Superclass::FixedImageType itk::KappaStatisticImageToImageMetric< TFixedImage, TMovingImage >::FixedImageType |
Definition at line 84 of file itkKappaStatisticImageToImageMetric.h.
typedef Superclass::GradientImageType itk::KappaStatisticImageToImageMetric< TFixedImage, TMovingImage >::GradientImageType |
Definition at line 77 of file itkKappaStatisticImageToImageMetric.h.
typedef Superclass::GradientPixelType itk::KappaStatisticImageToImageMetric< TFixedImage, TMovingImage >::GradientPixelType |
Definition at line 78 of file itkKappaStatisticImageToImageMetric.h.
typedef Superclass::InputPointType itk::KappaStatisticImageToImageMetric< TFixedImage, TMovingImage >::InputPointType |
Definition at line 79 of file itkKappaStatisticImageToImageMetric.h.
typedef Superclass::MeasureType itk::KappaStatisticImageToImageMetric< TFixedImage, TMovingImage >::MeasureType |
Definition at line 82 of file itkKappaStatisticImageToImageMetric.h.
typedef Superclass::MovingImageConstPointer itk::KappaStatisticImageToImageMetric< TFixedImage, TMovingImage >::MovingImageConstPointer |
Definition at line 87 of file itkKappaStatisticImageToImageMetric.h.
typedef Superclass::MovingImageType itk::KappaStatisticImageToImageMetric< TFixedImage, TMovingImage >::MovingImageType |
Definition at line 85 of file itkKappaStatisticImageToImageMetric.h.
typedef Superclass::OutputPointType itk::KappaStatisticImageToImageMetric< TFixedImage, TMovingImage >::OutputPointType |
Definition at line 80 of file itkKappaStatisticImageToImageMetric.h.
typedef SmartPointer< Self > itk::KappaStatisticImageToImageMetric< TFixedImage, TMovingImage >::Pointer |
Definition at line 62 of file itkKappaStatisticImageToImageMetric.h.
typedef Superclass::RealType itk::KappaStatisticImageToImageMetric< TFixedImage, TMovingImage >::RealType |
Types transferred from the base class
Definition at line 69 of file itkKappaStatisticImageToImageMetric.h.
typedef KappaStatisticImageToImageMetric itk::KappaStatisticImageToImageMetric< TFixedImage, TMovingImage >::Self |
Standard class typedefs.
Definition at line 60 of file itkKappaStatisticImageToImageMetric.h.
typedef ImageToImageMetric< TFixedImage, TMovingImage > itk::KappaStatisticImageToImageMetric< TFixedImage, TMovingImage >::Superclass |
Definition at line 61 of file itkKappaStatisticImageToImageMetric.h.
typedef Superclass::TransformJacobianType itk::KappaStatisticImageToImageMetric< TFixedImage, TMovingImage >::TransformJacobianType |
Definition at line 76 of file itkKappaStatisticImageToImageMetric.h.
typedef Superclass::TransformParametersType itk::KappaStatisticImageToImageMetric< TFixedImage, TMovingImage >::TransformParametersType |
Definition at line 75 of file itkKappaStatisticImageToImageMetric.h.
typedef Superclass::TransformPointer itk::KappaStatisticImageToImageMetric< TFixedImage, TMovingImage >::TransformPointer |
Definition at line 74 of file itkKappaStatisticImageToImageMetric.h.
typedef Superclass::TransformType itk::KappaStatisticImageToImageMetric< TFixedImage, TMovingImage >::TransformType |
Definition at line 73 of file itkKappaStatisticImageToImageMetric.h.
|
protected |
|
inlineprotectedvirtual |
Definition at line 126 of file itkKappaStatisticImageToImageMetric.h.
|
private |
|
virtual |
Set/Get whether this metric returns 2*|A&B|/(|A|+|B|) (ComplementOff, the default) or 1.0 - 2*|A&B|/(|A|+|B|) (ComplementOn). When using an optimizer that minimizes metric values use ComplementOn().
|
virtual |
Set/Get whether this metric returns 2*|A&B|/(|A|+|B|) (ComplementOff, the default) or 1.0 - 2*|A&B|/(|A|+|B|) (ComplementOn). When using an optimizer that minimizes metric values use ComplementOn().
|
virtual |
Computes the gradient image and assigns it to m_GradientImage
Reimplemented from itk::ImageToImageMetric< TFixedImage, TMovingImage >.
|
virtual |
Create an object from an instance, potentially deferring to a factory. This method allows you to create an instance of an object that is exactly the same type as the referring object. This is useful in cases where an object has been cast back to a base class.
Reimplemented from itk::Object.
|
virtual |
Set/Get whether this metric returns 2*|A&B|/(|A|+|B|) (ComplementOff, the default) or 1.0 - 2*|A&B|/(|A|+|B|) (ComplementOn). When using an optimizer that minimizes metric values use ComplementOn().
void itk::KappaStatisticImageToImageMetric< TFixedImage, TMovingImage >::GetDerivative | ( | const TransformParametersType & | , |
DerivativeType & | derivative | ||
) | const |
Get the derivatives of the match measure.
|
virtual |
This method allows the user to set the foreground value. The default value is 255.
|
virtual |
Run-time type information (and related methods).
Reimplemented from itk::ImageToImageMetric< TFixedImage, TMovingImage >.
MeasureType itk::KappaStatisticImageToImageMetric< TFixedImage, TMovingImage >::GetValue | ( | const TransformParametersType & | parameters | ) | const |
Get the value of the metric at a particular parameter setting. The metric value is given by 2*|A&B|/(|A|+|B|), where A is the moving image, B is the fixed image, & is intersection, and |.| indicates the area of the enclosed set. If ComplementOn has been set, the metric value is 1.0-2*|A&B|/(|A|+|B|).
void itk::KappaStatisticImageToImageMetric< TFixedImage, TMovingImage >::GetValueAndDerivative | ( | const TransformParametersType & | parameters, |
MeasureType & | Value, | ||
DerivativeType & | Derivative | ||
) | const |
Get both the value and derivative. This method internally calls the GetValue()
and the GetDerivative()
method.
|
static |
Method for creation through the object factory.
|
private |
|
protectedvirtual |
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::ImageToImageMetric< TFixedImage, TMovingImage >.
|
virtual |
Set/Get whether this metric returns 2*|A&B|/(|A|+|B|) (ComplementOff, the default) or 1.0 - 2*|A&B|/(|A|+|B|) (ComplementOn). When using an optimizer that minimizes metric values use ComplementOn().
|
virtual |
This method allows the user to set the foreground value. The default value is 255.
|
private |
Definition at line 134 of file itkKappaStatisticImageToImageMetric.h.
|
private |
Definition at line 133 of file itkKappaStatisticImageToImageMetric.h.