ITK
4.2.0
Insight Segmentation and Registration Toolkit
|
#include <itkRegistrationParameterScalesFromJacobian.h>
Public Types | |
typedef SmartPointer< const Self > | ConstPointer |
typedef Superclass::FixedTransformType | FixedTransformType |
typedef Superclass::FloatType | FloatType |
typedef Superclass::JacobianType | JacobianType |
typedef Superclass::MovingTransformType | MovingTransformType |
typedef Superclass::ParametersType | ParametersType |
typedef SmartPointer< Self > | Pointer |
typedef Superclass::ScalesType | ScalesType |
typedef RegistrationParameterScalesFromJacobian | Self |
typedef RegistrationParameterScalesEstimator < TMetric > | Superclass |
typedef Superclass::VirtualImageConstPointer | VirtualImageConstPointer |
typedef Superclass::VirtualIndexType | VirtualIndexType |
typedef Superclass::VirtualPointType | VirtualPointType |
Public Types inherited from itk::RegistrationParameterScalesEstimator< TMetric > | |
typedef FixedTransformType::ConstPointer | FixedTransformConstPointer |
typedef MetricType::ConstPointer | MetricConstPointer |
typedef MetricType::Pointer | MetricPointer |
typedef TMetric | MetricType |
typedef MovingTransformType::ConstPointer | MovingTransformConstPointer |
typedef std::vector < VirtualPointType > | SamplePointContainerType |
enum | SamplingStrategyType { FullDomainSampling = 0, CornerSampling, RandomSampling, CentralRegionSampling, VirtualDomainPointSetSampling } |
typedef TMetric::VirtualImagePointer | VirtualImagePointer |
typedef TMetric::VirtualImageType | VirtualImageType |
typedef TMetric::VirtualPointSetPointer | VirtualPointSetPointer |
typedef TMetric::VirtualPointSetType | VirtualPointSetType |
typedef TMetric::VirtualRegionType | VirtualRegionType |
typedef TMetric::VirtualSizeType | VirtualSizeType |
typedef TMetric::VirtualSpacingType | VirtualSpacingType |
Public Types inherited from itk::OptimizerParameterScalesEstimator | |
Public Types inherited from itk::Object | |
Public Types inherited from itk::LightObject |
Public Member Functions | |
virtual ::itk::LightObject::Pointer | CreateAnother (void) const |
virtual void | EstimateLocalStepScales (const ParametersType &step, ScalesType &localStepScales) |
virtual void | EstimateScales (ScalesType &scales) |
virtual FloatType | EstimateStepScale (const ParametersType &step) |
virtual const char * | GetNameOfClass () const |
Public Member Functions inherited from itk::RegistrationParameterScalesEstimator< TMetric > | |
virtual FloatType | EstimateMaximumStepSize () |
virtual void | SetCentralRegionRadius (IndexValueType _arg) |
virtual void | SetMetric (MetricType *_arg) |
virtual void | SetScalesSamplingStrategy () |
virtual void | SetStepScaleSamplingStrategy () |
virtual void | SetTransformForward (bool _arg) |
virtual bool | GetTransformForward () const |
virtual void | SetVirtualDomainPointSet (VirtualPointSetType *_arg) |
virtual void | SetVirtualDomainPointSet (const VirtualPointSetType *_arg) |
virtual const VirtualPointSetType * | GetVirtualDomainPointSet () |
Static Public Member Functions | |
static Pointer | New () |
Private Member Functions | |
void | operator= (const Self &) |
RegistrationParameterScalesFromJacobian (const Self &) |
Additional Inherited Members | |
Static Public Attributes inherited from itk::RegistrationParameterScalesEstimator< TMetric > | |
static const SizeValueType | FixedDimension = TMetric::FixedDimension |
static const SizeValueType | MovingDimension = TMetric::MovingDimension |
static const SizeValueType | VirtualDimension = TMetric::VirtualDimension |
Protected Attributes inherited from itk::RegistrationParameterScalesEstimator< TMetric > | |
IndexValueType | m_CentralRegionRadius |
MetricPointer | m_Metric |
SizeValueType | m_NumberOfRandomSamples |
SamplePointContainerType | m_SamplePoints |
TimeStamp | m_SamplingTime |
VirtualPointSetType::ConstPointer | m_VirtualDomainPointSet |
Static Protected Attributes inherited from itk::RegistrationParameterScalesEstimator< TMetric > | |
static const SizeValueType | SizeOfSmallDomain = 1000 |
Implements a registration helper class for estimating scales of transform parameters from Jacobian norms.
Its input includes the fixed/moving images and transform objects, which can be obtained from the metric object.
The scale of a parameter is estimated from the averaged squared norm of the Jacobian w.r.t the parameter. The averaging is done over a sampling of the image domain. The sampling by default is a uniform random distribution.
Definition at line 41 of file itkRegistrationParameterScalesFromJacobian.h.
typedef SmartPointer<const Self> itk::RegistrationParameterScalesFromJacobian< TMetric >::ConstPointer |
Reimplemented from itk::RegistrationParameterScalesEstimator< TMetric >.
Definition at line 49 of file itkRegistrationParameterScalesFromJacobian.h.
typedef Superclass::FixedTransformType itk::RegistrationParameterScalesFromJacobian< TMetric >::FixedTransformType |
Type of the transform to initialize
Reimplemented from itk::RegistrationParameterScalesEstimator< TMetric >.
Definition at line 69 of file itkRegistrationParameterScalesFromJacobian.h.
typedef Superclass::FloatType itk::RegistrationParameterScalesFromJacobian< TMetric >::FloatType |
Type of float
Reimplemented from itk::RegistrationParameterScalesEstimator< TMetric >.
Definition at line 64 of file itkRegistrationParameterScalesFromJacobian.h.
typedef Superclass::JacobianType itk::RegistrationParameterScalesFromJacobian< TMetric >::JacobianType |
Type of Jacobian of transform.
Reimplemented from itk::RegistrationParameterScalesEstimator< TMetric >.
Definition at line 70 of file itkRegistrationParameterScalesFromJacobian.h.
typedef Superclass::MovingTransformType itk::RegistrationParameterScalesFromJacobian< TMetric >::MovingTransformType |
Reimplemented from itk::RegistrationParameterScalesEstimator< TMetric >.
Definition at line 68 of file itkRegistrationParameterScalesFromJacobian.h.
typedef Superclass::ParametersType itk::RegistrationParameterScalesFromJacobian< TMetric >::ParametersType |
Type of parameters of the optimizer
Reimplemented from itk::RegistrationParameterScalesEstimator< TMetric >.
Definition at line 61 of file itkRegistrationParameterScalesFromJacobian.h.
typedef SmartPointer<Self> itk::RegistrationParameterScalesFromJacobian< TMetric >::Pointer |
Reimplemented from itk::RegistrationParameterScalesEstimator< TMetric >.
Definition at line 48 of file itkRegistrationParameterScalesFromJacobian.h.
typedef Superclass::ScalesType itk::RegistrationParameterScalesFromJacobian< TMetric >::ScalesType |
Type of scales
Reimplemented from itk::RegistrationParameterScalesEstimator< TMetric >.
Definition at line 55 of file itkRegistrationParameterScalesFromJacobian.h.
typedef RegistrationParameterScalesFromJacobian itk::RegistrationParameterScalesFromJacobian< TMetric >::Self |
Standard class typedefs.
Reimplemented from itk::RegistrationParameterScalesEstimator< TMetric >.
Definition at line 46 of file itkRegistrationParameterScalesFromJacobian.h.
typedef RegistrationParameterScalesEstimator< TMetric > itk::RegistrationParameterScalesFromJacobian< TMetric >::Superclass |
Reimplemented from itk::RegistrationParameterScalesEstimator< TMetric >.
Definition at line 47 of file itkRegistrationParameterScalesFromJacobian.h.
typedef Superclass::VirtualImageConstPointer itk::RegistrationParameterScalesFromJacobian< TMetric >::VirtualImageConstPointer |
Reimplemented from itk::RegistrationParameterScalesEstimator< TMetric >.
Definition at line 71 of file itkRegistrationParameterScalesFromJacobian.h.
typedef Superclass::VirtualIndexType itk::RegistrationParameterScalesFromJacobian< TMetric >::VirtualIndexType |
Reimplemented from itk::RegistrationParameterScalesEstimator< TMetric >.
Definition at line 67 of file itkRegistrationParameterScalesFromJacobian.h.
typedef Superclass::VirtualPointType itk::RegistrationParameterScalesFromJacobian< TMetric >::VirtualPointType |
Reimplemented from itk::RegistrationParameterScalesEstimator< TMetric >.
Definition at line 66 of file itkRegistrationParameterScalesFromJacobian.h.
|
protected |
|
inlineprotected |
Definition at line 101 of file itkRegistrationParameterScalesFromJacobian.h.
|
private |
|
protected |
Compute the step scales for samples, i.e. the impacts on each sampled voxel from a change on the transform.
|
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 |
Estimate the scales of local steps.
Implements itk::RegistrationParameterScalesEstimator< TMetric >.
|
virtual |
Estimate parameter scales.
Implements itk::RegistrationParameterScalesEstimator< TMetric >.
|
virtual |
Estimate the scale for , the step of change on parameters. The step scale describes the impact of on the transform.
Let us denote the transform by
where is the coordinates of a voxel, is the transform parameters, and is the step factor.
At a specific voxel at , the step scale w.r.t. is defined here as
For multiple voxels, we average the above formula to get the overall step scale.
Implements itk::RegistrationParameterScalesEstimator< TMetric >.
|
virtual |
Run-time type information (and related methods).
Reimplemented from itk::RegistrationParameterScalesEstimator< TMetric >.
|
static |
New macro for creation of through a Smart Pointer.
Reimplemented from itk::Object.
|
private |
Mutex lock to protect modification to the reference count
Reimplemented from itk::RegistrationParameterScalesEstimator< TMetric >.
|
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::RegistrationParameterScalesEstimator< TMetric >.