ITK  4.1.0
Insight Segmentation and Registration Toolkit
Public Types | Public Member Functions | Static Public Member Functions | Protected Member Functions | Private Attributes
itk::OnePlusOneEvolutionaryOptimizer Class Reference

#include <itkOnePlusOneEvolutionaryOptimizer.h>

+ Inheritance diagram for itk::OnePlusOneEvolutionaryOptimizer:
+ Collaboration diagram for itk::OnePlusOneEvolutionaryOptimizer:

List of all members.

Public Types

typedef SmartPointer< const SelfConstPointer
typedef CostFunctionType::Pointer CostFunctionPointer
typedef SingleValuedCostFunction CostFunctionType
typedef
Statistics::RandomVariateGeneratorBase 
NormalVariateGeneratorType
typedef SmartPointer< SelfPointer
typedef
OnePlusOneEvolutionaryOptimizer 
Self
typedef
SingleValuedNonLinearOptimizer 
Superclass

Public Member Functions

virtual ::itk::LightObject::Pointer CreateAnother (void) const
virtual const bool & GetCatchGetValueException ()
virtual const unsigned int & GetCurrentIteration ()
virtual const double & GetFrobeniusNorm ()
virtual const bool & GetInitialized ()
virtual const double & GetMetricWorstPossibleValue ()
bool GetMinimize () const
virtual const char * GetNameOfClass () const
const std::string GetStopConditionDescription () const
void Initialize (double initialRadius, double grow=-1, double shrink=-1)
void MinimizeOff (void)
void MinimizeOn (void)
virtual void SetCatchGetValueException (bool _arg)
virtual void SetMetricWorstPossibleValue (double _arg)
void SetMinimize (bool v)
void SetNormalVariateGenerator (NormalVariateGeneratorType *generator)
void StartOptimization ()
void StopOptimization ()
virtual void SetMaximize (bool _arg)
virtual void MaximizeOn ()
virtual void MaximizeOff ()
virtual const bool & GetMaximize ()
virtual void SetMaximumIteration (unsigned int _arg)
virtual const unsigned int & GetMaximumIteration ()
virtual void SetGrowthFactor (double _arg)
virtual const double & GetGrowthFactor ()
virtual void SetShrinkFactor (double _arg)
virtual const double & GetShrinkFactor ()
virtual void SetInitialRadius (double _arg)
virtual const double & GetInitialRadius ()
virtual void SetEpsilon (double _arg)
virtual const double & GetEpsilon ()
virtual const MeasureTypeGetCurrentCost ()
MeasureType GetValue () const

Static Public Member Functions

static Pointer New ()

Protected Member Functions

 OnePlusOneEvolutionaryOptimizer ()
 OnePlusOneEvolutionaryOptimizer (const OnePlusOneEvolutionaryOptimizer &)
void PrintSelf (std::ostream &os, Indent indent) const
virtual ~OnePlusOneEvolutionaryOptimizer ()

Private Attributes

bool m_CatchGetValueException
MeasureType m_CurrentCost
unsigned int m_CurrentIteration
double m_Epsilon
double m_FrobeniusNorm
double m_GrowthFactor
bool m_Initialized
double m_InitialRadius
bool m_Maximize
unsigned int m_MaximumIteration
double m_MetricWorstPossibleValue
NormalVariateGeneratorType::Pointer m_RandomGenerator
double m_ShrinkFactor
bool m_Stop
std::ostringstream m_StopConditionDescription

Detailed Description

1+1 evolutionary strategy optimizer

This optimizer searches for the optimal parameters. It changes its search radius and position using the grow factor ,shrink factor, and isotropic probability function (which is a random unit normal variate generator).

This optimizer needs a cost function and a random unit normal variate generator. The cost function should return cost with new position in parameter space which will be generated by 1+1 evolutionary strategy. Users should plug-in the random unit normal variate generator using SetNormalVariateGenerator method.

The SetEpsilon method is the minimum value for the frobenius_norm of the covariance matrix. If the fnorm is smaller than this value, the optimization process will stop even before it hits the maximum iteration.

Another way to stop the optimization process is calling the StopOptimization method. At next iteration after calling it, the optimization process will stop.

This optimizing scheme was initially developed and implemented by Martin Styner, Univ. of North Carolina at Chapel Hill, and his colleagues.

For more details. refer to the following articles. "Parametric estimate of intensity inhomogeneities applied to MRI" Martin Styner, G. Gerig, Christian Brechbuehler, Gabor Szekely, IEEE TRANSACTIONS ON MEDICAL IMAGING; 19(3), pp. 153-165, 2000, (http://www.cs.unc.edu/~styner/docs/tmi00.pdf)

"Evaluation of 2D/3D bias correction with 1+1ES-optimization" Martin Styner, Prof. Dr. G. Gerig (IKT, BIWI, ETH Zuerich), TR-197 (http://www.cs.unc.edu/~styner/docs/StynerTR97.pdf)

See also:
NormalVariateGenerator

Definition at line 70 of file itkOnePlusOneEvolutionaryOptimizer.h.


Member Typedef Documentation

Reimplemented from itk::SingleValuedNonLinearOptimizer.

Definition at line 78 of file itkOnePlusOneEvolutionaryOptimizer.h.

Reimplemented from itk::SingleValuedNonLinearOptimizer.

Definition at line 88 of file itkOnePlusOneEvolutionaryOptimizer.h.

Type of the Cost Function

Reimplemented from itk::SingleValuedNonLinearOptimizer.

Definition at line 84 of file itkOnePlusOneEvolutionaryOptimizer.h.

Normal random variate generator type.

Definition at line 91 of file itkOnePlusOneEvolutionaryOptimizer.h.

Reimplemented from itk::SingleValuedNonLinearOptimizer.

Definition at line 77 of file itkOnePlusOneEvolutionaryOptimizer.h.

Standard "Self" typedef.

Reimplemented from itk::SingleValuedNonLinearOptimizer.

Definition at line 75 of file itkOnePlusOneEvolutionaryOptimizer.h.

Reimplemented from itk::SingleValuedNonLinearOptimizer.

Definition at line 76 of file itkOnePlusOneEvolutionaryOptimizer.h.


Constructor & Destructor Documentation


Member Function Documentation

virtual::itk::LightObject::Pointer itk::OnePlusOneEvolutionaryOptimizer::CreateAnother ( void  ) const [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::SingleValuedNonLinearOptimizer.

Return Current Value

virtual const unsigned int& itk::OnePlusOneEvolutionaryOptimizer::GetCurrentIteration ( ) [virtual]

Return Current Iteration

virtual const double& itk::OnePlusOneEvolutionaryOptimizer::GetEpsilon ( ) [virtual]

Set/Get the minimal size of search radius (frobenius_norm of covariance matrix).

virtual const double& itk::OnePlusOneEvolutionaryOptimizer::GetFrobeniusNorm ( ) [virtual]

Get the current Frobenius norm of covariance matrix

virtual const double& itk::OnePlusOneEvolutionaryOptimizer::GetGrowthFactor ( ) [virtual]

Set/Get the search radius grow factor in parameter space.

virtual const bool& itk::OnePlusOneEvolutionaryOptimizer::GetInitialized ( ) [virtual]

Return if optimizer has been initialized

virtual const double& itk::OnePlusOneEvolutionaryOptimizer::GetInitialRadius ( ) [virtual]

Set/Get initial search radius in parameter space

virtual const bool& itk::OnePlusOneEvolutionaryOptimizer::GetMaximize ( ) [virtual]

Set if the Optimizer should Maximize the metric

virtual const unsigned int& itk::OnePlusOneEvolutionaryOptimizer::GetMaximumIteration ( ) [virtual]

Set/Get maximum iteration limit.

Definition at line 99 of file itkOnePlusOneEvolutionaryOptimizer.h.

virtual const char* itk::OnePlusOneEvolutionaryOptimizer::GetNameOfClass ( ) const [virtual]

Run-time type information (and related methods).

Reimplemented from itk::SingleValuedNonLinearOptimizer.

virtual const double& itk::OnePlusOneEvolutionaryOptimizer::GetShrinkFactor ( ) [virtual]

Set/Get the search radius shrink factor.

Get the reason for termination

Reimplemented from itk::Optimizer.

Return Current Value

Definition at line 149 of file itkOnePlusOneEvolutionaryOptimizer.h.

void itk::OnePlusOneEvolutionaryOptimizer::Initialize ( double  initialRadius,
double  grow = -1,
double  shrink = -1 
)

Initializes the optimizer. Before running this optimizer, this function should have been called.

initialRadius: search radius in parameter space grow: search radius grow factor shrink: searhc radius shrink factor

Set if the Optimizer should Maximize the metric

Set if the Optimizer should Maximize the metric

Definition at line 105 of file itkOnePlusOneEvolutionaryOptimizer.h.

Definition at line 103 of file itkOnePlusOneEvolutionaryOptimizer.h.

Method for creation through the object factory.

Reimplemented from itk::SingleValuedNonLinearOptimizer.

void itk::OnePlusOneEvolutionaryOptimizer::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::SingleValuedNonLinearOptimizer.

virtual void itk::OnePlusOneEvolutionaryOptimizer::SetEpsilon ( double  _arg) [virtual]

Set/Get the minimal size of search radius (frobenius_norm of covariance matrix).

virtual void itk::OnePlusOneEvolutionaryOptimizer::SetGrowthFactor ( double  _arg) [virtual]

Set/Get the search radius grow factor in parameter space.

virtual void itk::OnePlusOneEvolutionaryOptimizer::SetInitialRadius ( double  _arg) [virtual]

Set/Get initial search radius in parameter space

virtual void itk::OnePlusOneEvolutionaryOptimizer::SetMaximize ( bool  _arg) [virtual]

Set if the Optimizer should Maximize the metric

virtual void itk::OnePlusOneEvolutionaryOptimizer::SetMaximumIteration ( unsigned int  _arg) [virtual]

Set/Get maximum iteration limit.

Definition at line 101 of file itkOnePlusOneEvolutionaryOptimizer.h.

virtual void itk::OnePlusOneEvolutionaryOptimizer::SetShrinkFactor ( double  _arg) [virtual]

Set/Get the search radius shrink factor.

Start optimization. Optimization will stop when it meets either of two termination conditions, the maximum iteration limit or epsilon (minimal search radius)

Reimplemented from itk::Optimizer.

when users call StartOptimization, this value will be set false. By calling StopOptimization, this flag will be set true, and optimization will stop at the next iteration.

Definition at line 166 of file itkOnePlusOneEvolutionaryOptimizer.h.


Member Data Documentation

Definition at line 194 of file itkOnePlusOneEvolutionaryOptimizer.h.

Internal storage for the value type / used as a cache

Definition at line 217 of file itkOnePlusOneEvolutionaryOptimizer.h.

Current iteration

Definition at line 192 of file itkOnePlusOneEvolutionaryOptimizer.h.

The minimal size of search radius (frobenius_norm of covariance matrix).

Definition at line 202 of file itkOnePlusOneEvolutionaryOptimizer.h.

Cache variable for reporting the Frobenius Norm

Definition at line 230 of file itkOnePlusOneEvolutionaryOptimizer.h.

Search radius growth factor in parameter space.

Definition at line 208 of file itkOnePlusOneEvolutionaryOptimizer.h.

Flag tells if the optimizer was initialized using Initialize function.

Definition at line 214 of file itkOnePlusOneEvolutionaryOptimizer.h.

Initial search radius in parameter space.

Definition at line 205 of file itkOnePlusOneEvolutionaryOptimizer.h.

Set if the Metric should be maximized: Default = False

Definition at line 198 of file itkOnePlusOneEvolutionaryOptimizer.h.

Maximum iteration limit.

Definition at line 189 of file itkOnePlusOneEvolutionaryOptimizer.h.

Definition at line 195 of file itkOnePlusOneEvolutionaryOptimizer.h.

Smart pointer to the normal random variate generator.

Definition at line 186 of file itkOnePlusOneEvolutionaryOptimizer.h.

Search radius shrink factor in parameter space,

Definition at line 211 of file itkOnePlusOneEvolutionaryOptimizer.h.

This is user-settable flag to stop optimization. when users call StartOptimization, this value will be set false. By calling StopOptimization, this flag will be set true, and optimization will stop at the next iteration.

Definition at line 223 of file itkOnePlusOneEvolutionaryOptimizer.h.

Stop description

Definition at line 226 of file itkOnePlusOneEvolutionaryOptimizer.h.


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