ITK  4.1.0
Insight Segmentation and Registration Toolkit
Public Types | Public Member Functions | Static Public Member Functions | Protected Member Functions | Protected Attributes | Private Member Functions
itk::MultiStartOptimizerv4 Class Reference

#include <itkMultiStartOptimizerv4.h>

+ Inheritance diagram for itk::MultiStartOptimizerv4:
+ Collaboration diagram for itk::MultiStartOptimizerv4:

List of all members.

Public Types

typedef SmartPointer< const SelfConstPointer
typedef MetricType::DerivativeType DerivativeType
typedef
Superclass::InternalComputationValueType 
InternalComputationValueType
typedef
itk::GradientDescentOptimizerv4::Pointer 
LocalOptimizerPointer
typedef
itk::GradientDescentOptimizerv4 
LocalOptimizerType
typedef Superclass::MeasureType MeasureType
typedef Superclass::MetricType MetricType
typedef MetricType::Pointer MetricTypePointer
typedef std::vector< MeasureTypeMetricValuesListType
typedef OptimizerType::Pointer OptimizerPointer
typedef ObjectToObjectOptimizerBase OptimizerType
typedef
ParametersListType::size_type 
ParameterListSizeType
typedef std::vector
< ParametersType
ParametersListType
typedef Superclass::ParametersType ParametersType
typedef SmartPointer< SelfPointer
typedef MultiStartOptimizerv4 Self
typedef std::ostringstream StopConditionDescriptionType
typedef std::string StopConditionReturnStringType
enum  StopConditionType {
  MAXIMUM_NUMBER_OF_ITERATIONS,
  COSTFUNCTION_ERROR,
  UPDATE_PARAMETERS_ERROR,
  STEP_TOO_SMALL,
  CONVERGENCE_CHECKER_PASSED,
  OTHER_ERROR
}
typedef ObjectToObjectOptimizerBase Superclass

Public Member Functions

virtual ::itk::LightObject::Pointer CreateAnother (void) const
ParametersType GetBestParameters ()
ParameterListSizeType GetBestParametersIndex ()
virtual SizeValueType GetCurrentIteration () const
const MetricValuesListTypeGetMetricValuesList () const
virtual const char * GetNameOfClass () const
virtual const SizeValueTypeGetNumberOfIterations ()
ParametersListTypeGetParametersList ()
virtual const StopConditionTypeGetStopCondition ()
virtual const
StopConditionReturnStringType 
GetStopConditionDescription () const
void InstantiateLocalOptimizer (void)
virtual void ResumeOptimization ()
virtual void SetNumberOfIterations (SizeValueType _arg)
void SetParametersList (ParametersListType &p)
virtual void StartOptimization (void)
virtual void StopOptimization (void)
virtual void SetLocalOptimizer (OptimizerType *_arg)
virtual OptimizerTypeGetLocalOptimizer ()

Static Public Member Functions

static Pointer New ()

Protected Member Functions

virtual void PrintSelf (std::ostream &os, Indent indent) const
 MultiStartOptimizerv4 ()
virtual ~MultiStartOptimizerv4 ()

Protected Attributes

ParameterListSizeType m_BestParametersIndex
SizeValueType m_CurrentIteration
OptimizerPointer m_LocalOptimizer
MeasureType m_MaximumMetricValue
MetricValuesListType m_MetricValuesList
MeasureType m_MinimumMetricValue
SizeValueType m_NumberOfIterations
ParametersListType m_ParametersList
bool m_Stop
StopConditionType m_StopCondition
StopConditionDescriptionType m_StopConditionDescription

Private Member Functions

 MultiStartOptimizerv4 (const Self &)
void operator= (const Self &)

Detailed Description

Multi-start searches over input parameters and returns the best metric value.

The multi-start algorithm performs gradient descent from N (large) number of starting points and returns the best solution. Ideal start points would sample the solution space almost uniformly, thus, in theory, this is a global optimizer. In this implementation, the quality of the optimization depends on the parameter space samples that the user inputs to the optimizer. Multi-start can be modified in numerous ways to improve robustness of standard approaches. These improvements usually focus modifying the parameter sample space. This is why we place the burden on the user to provide the parameter samples over which to optimize.

Definition at line 39 of file itkMultiStartOptimizerv4.h.


Member Typedef Documentation

Reimplemented from itk::ObjectToObjectOptimizerBase.

Definition at line 47 of file itkMultiStartOptimizerv4.h.

typedef MetricType::DerivativeType itk::MultiStartOptimizerv4::DerivativeType

Derivative type

Definition at line 84 of file itkMultiStartOptimizerv4.h.

Internal computation type, for maintaining a desired precision

Reimplemented from itk::ObjectToObjectOptimizerBase.

Definition at line 91 of file itkMultiStartOptimizerv4.h.

Definition at line 61 of file itkMultiStartOptimizerv4.h.

Definition at line 60 of file itkMultiStartOptimizerv4.h.

Measure type

Reimplemented from itk::ObjectToObjectOptimizerBase.

Definition at line 87 of file itkMultiStartOptimizerv4.h.

Metric type over which this class is templated

Reimplemented from itk::ObjectToObjectOptimizerBase.

Definition at line 80 of file itkMultiStartOptimizerv4.h.

typedef MetricType::Pointer itk::MultiStartOptimizerv4::MetricTypePointer

Reimplemented from itk::ObjectToObjectOptimizerBase.

Definition at line 81 of file itkMultiStartOptimizerv4.h.

Definition at line 88 of file itkMultiStartOptimizerv4.h.

Definition at line 59 of file itkMultiStartOptimizerv4.h.

Definition at line 58 of file itkMultiStartOptimizerv4.h.

typedef ParametersListType::size_type itk::MultiStartOptimizerv4::ParameterListSizeType

Definition at line 57 of file itkMultiStartOptimizerv4.h.

Definition at line 56 of file itkMultiStartOptimizerv4.h.

Parameters type.

Reimplemented from itk::ObjectToObjectOptimizerBase.

Definition at line 53 of file itkMultiStartOptimizerv4.h.

Reimplemented from itk::ObjectToObjectOptimizerBase.

Definition at line 46 of file itkMultiStartOptimizerv4.h.

Standard class typedefs.

Reimplemented from itk::ObjectToObjectOptimizerBase.

Definition at line 44 of file itkMultiStartOptimizerv4.h.

Stop condition internal string type

Definition at line 77 of file itkMultiStartOptimizerv4.h.

Stop condition return string type

Definition at line 74 of file itkMultiStartOptimizerv4.h.

Reimplemented from itk::ObjectToObjectOptimizerBase.

Definition at line 45 of file itkMultiStartOptimizerv4.h.


Member Enumeration Documentation

Codes of stopping conditions.

Enumerator:
MAXIMUM_NUMBER_OF_ITERATIONS 
COSTFUNCTION_ERROR 
UPDATE_PARAMETERS_ERROR 
STEP_TOO_SMALL 
CONVERGENCE_CHECKER_PASSED 
OTHER_ERROR 

Definition at line 64 of file itkMultiStartOptimizerv4.h.


Constructor & Destructor Documentation

Default constructor

virtual itk::MultiStartOptimizerv4::~MultiStartOptimizerv4 ( ) [protected, virtual]

Default constructor


Member Function Documentation

virtual::itk::LightObject::Pointer itk::MultiStartOptimizerv4::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::Object.

Return the parameters from the best visited position

Definition at line 139 of file itkMultiStartOptimizerv4.h.

Get the current iteration number.

Set/Get the optimizer.

Get the list of metric values that we produced after the multi-start search.

virtual const char* itk::MultiStartOptimizerv4::GetNameOfClass ( ) const [virtual]

Run-time type information (and related methods).

Reimplemented from itk::ObjectToObjectOptimizerBase.

Get the number of iterations.

Get the list of parameters over which to search.

Get stop condition enum

Get the reason for termination

Create an instance of the local optimizer

Method for creation through the object factory.

Reimplemented from itk::Object.

void itk::MultiStartOptimizerv4::operator= ( const Self ) [private]

Mutex lock to protect modification to the reference count

Reimplemented from itk::ObjectToObjectOptimizerBase.

virtual void itk::MultiStartOptimizerv4::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::ObjectToObjectOptimizerBase.

Resume the optimization. Can be called after StopOptimization to resume. The bulk of the optimization work loop is here.

Set/Get the optimizer.

Set the number of iterations.

Set the list of parameters over which to search

virtual void itk::MultiStartOptimizerv4::StartOptimization ( void  ) [virtual]

Begin the optimization

Reimplemented from itk::ObjectToObjectOptimizerBase.

virtual void itk::MultiStartOptimizerv4::StopOptimization ( void  ) [virtual]

Stop optimization. The object is left in a state so the optimization can be resumed by calling ResumeOptimization.


Member Data Documentation

Definition at line 160 of file itkMultiStartOptimizerv4.h.

Definition at line 155 of file itkMultiStartOptimizerv4.h.

Definition at line 161 of file itkMultiStartOptimizerv4.h.

Definition at line 159 of file itkMultiStartOptimizerv4.h.

Definition at line 157 of file itkMultiStartOptimizerv4.h.

Definition at line 158 of file itkMultiStartOptimizerv4.h.

Definition at line 154 of file itkMultiStartOptimizerv4.h.

Definition at line 156 of file itkMultiStartOptimizerv4.h.

Definition at line 151 of file itkMultiStartOptimizerv4.h.

Definition at line 152 of file itkMultiStartOptimizerv4.h.

Definition at line 153 of file itkMultiStartOptimizerv4.h.


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