zxhOptimizerGradientLocalAffines Class Reference

optimizers search for the optimal value of the metric within the transformation follow gradient direction More...

#include <zxhOptimizerGradientLocalAffines.h>

Inheritance diagram for zxhOptimizerGradientLocalAffines:

List of all members.

Public Member Functions
	zxhOptimizerGradientLocalAffines (void)
	constructor
	~zxhOptimizerGradientLocalAffines (void)
	deconstructor
virtual std::string	GetPrintString ()
virtual bool	SetOptimizerFromStream (std::ifstream &ifs)
	from stream
virtual zxhOptimizerBase *	Clone (zxhOptimizerBase *&pRet)
virtual void	SetOptimisationSteps (int nGlobal, int nLocal)
virtual void	Run ()
	for running registration to search optimal
virtual void	Run2 ()
	for running registration to search optimal using estimation from local movement trends
virtual bool	AdjustParameters (bool forceconcatenation=false)
	regularistion :adjust transform, metric, gradient, differentialstep, ....
void	AdjustGradientAdvanceStep (zxhTransformBase *pTransformAdvanceStep, zxhTransformBase *pGradient)
virtual void	SetPreGlobalRegistration (int i)
virtual void	SetAccessoryLocalRegions (bool b)
virtual bool	GetAccessoryLocalRegions ()
Protected Attributes
int	m_nGlobalAffine
	number of iteration for global affine in each optimisation step
int	m_nLocalAffines
int	m_nPreGlobalRegistration
bool	m_bAccessoryLocalRegions
	Accessory local regions to the target tand source for computing the cost function.

---

Detailed Description

optimizers search for the optimal value of the metric within the transformation follow gradient direction

---

Member Function Documentation

void zxhOptimizerGradientLocalAffines::AdjustGradientAdvanceStep	(	zxhTransformBase *	pTransformAdvanceStep,
		zxhTransformBase *	pGradient
	)

advance of each affine is independent on each other but related to Gaussian distribution of displacement length hence we optimise local affines non-competitatively because --- current not used

advance of each affine is independent on each other but related to Gaussian distribution of displacement length hence we optimise local affines non-competitatively because --- current not used

zxhOptimizerBase * zxhOptimizerGradientLocalAffines::Clone

(

zxhOptimizerBase *&

pRet

)

[virtual]

Returns:

Reimplemented from zxhOptimizerGradient.

Reimplemented in zxhOptimizerGradientLocalMatrix.

std::string zxhOptimizerGradientLocalAffines::GetPrintString

(

)

[virtual]

Returns:

Reimplemented from zxhOptimizerGradient.

---

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

• zxhOptimizerGradientLocalAffines.h
• zxhOptimizerGradientLocalAffines.cpp