CVB++ 14.0
ClassifierFactory Class Reference

Learner object that creates a classifier from an image list. More...

#include <cvb/minos/classifier_factory.hpp>

Public Member Functions

std::unique_ptr< ClassifierLearn (const TrainingSet &trainingSet)
 Learn a new classifier from the trainingSet using the parameters stored in the properties of this object. More...
 
int IndifferenceRadius () const noexcept
 Get the minimum distance to be assumed between a (labeled) positive sample and a counter sample in a training set image. More...
 
void SetIndifferenceRadius (int indifferenceRadius)
 Set the minimum distance to be assumed between a (labeled) positive sample and a counter sample in a training set image. More...
 
double NegativeDensity () const noexcept
 Get the scan density with which to extract counter samples from the training set images. More...
 
void SetNegativeDensity (double negativeDensity)
 Set the scan density with which to extract counter samples from the training set images. Higher densities will lead to a classifier that is potentially more robust versus false positive detections, but will also result in increased learning times. More...
 
int ContrastTrigger () const noexcept
 Get the minimum contrast a Minos feature must achieve before it is eligible to become part of the classifier. More...
 
void SetContrastTrigger (int contrastTrigger)
 Set the minimum contrast a Minos feature must achieve before it is eligible to become part of the classifier. Lower values will lead to a classifier that is more sensitive in low-contrast situation but might also increase the number of false positive results that need to be filtered out e.g. by means of their quality measure. More...
 
int EnsembleSize () const noexcept
 Get the maximum size of the Ensembles of similar instance images to be used for pair feature calculation. More...
 
void SetEnsembleSize (int ensembleSize)
 Set the maximum size of the Ensembles of similar instance images to be used for pair feature calculation. Valid ensemble sizes must be greater than 0, the default value is 15. More...
 
int Polydromy () const noexcept
 Get the polydromy value controlling the complexity of the feature search tree in the classifier. More...
 
void SetPolydromy (int polydromy)
 Set the polydromy value controlling the complexity of the feature search tree in the classifier. Valid polydromy values must be greater than 0, the default value is 2. More...
 
int MinPairFeatures () const noexcept
 Get the minimum number of features to extract for each model when building a classifier. More...
 
void SetMinPairFeatures (int minPairFeatures)
 Set the minimum number of features to extract for each model when building a classifier. More...
 

Static Public Member Functions

static int IndifferenceRadiusDefault () noexcept
 Default value for the IndifferenceRadius. More...
 
static double NegativeDensityDefault () noexcept
 Default value for the NegativeDensity. More...
 
static int ContrastTriggerDefault () noexcept
 Default value for the ContrastTrigger. More...
 
static int EnsembleSizeDefault () noexcept
 Default value for the EnsembleSize. More...
 
static int PolydromyDefault () noexcept
 Default value for the Polydromy. More...
 
static int MinPairFeaturesDefault () noexcept
 Default value for the MinPairFeatures. More...
 

Detailed Description

Learner object that creates a classifier from an image list.

Member Function Documentation

◆ ContrastTrigger()

int ContrastTrigger ( ) const
inlinenoexcept

Get the minimum contrast a Minos feature must achieve before it is eligible to become part of the classifier.

Returns
The contrast trigger value.
Exceptions
Doesnot throw any exception.

◆ ContrastTriggerDefault()

static int ContrastTriggerDefault ( )
inlinestaticnoexcept

Default value for the ContrastTrigger.

Returns
Default constrast trigger value.
Exceptions
Doesnot throw any exception.

◆ EnsembleSize()

int EnsembleSize ( ) const
inlinenoexcept

Get the maximum size of the Ensembles of similar instance images to be used for pair feature calculation.

Returns
The ensemble size value.
Exceptions
Doesnot throw any exception.

◆ EnsembleSizeDefault()

static int EnsembleSizeDefault ( )
inlinestaticnoexcept

Default value for the EnsembleSize.

Returns
Default ensemble size value.
Exceptions
Doesnot throw any exception.

◆ IndifferenceRadius()

int IndifferenceRadius ( ) const
inlinenoexcept

Get the minimum distance to be assumed between a (labeled) positive sample and a counter sample in a training set image.

Returns
The indifference radius value.
Exceptions
Doesnot throw any exception.

◆ IndifferenceRadiusDefault()

static int IndifferenceRadiusDefault ( )
inlinestaticnoexcept

Default value for the IndifferenceRadius.

Returns
Default indeference radius value.
Exceptions
Doesnot throw any exception.

◆ Learn()

std::unique_ptr< Classifier > Learn ( const TrainingSet trainingSet)
inline

Learn a new classifier from the trainingSet using the parameters stored in the properties of this object.

Parameters
[in]trainingSetTraining set from which to learn.
Returns
Newly learned classifier object.
Exceptions
Anyexception derived from std::exception including CvbException.

◆ MinPairFeatures()

int MinPairFeatures ( ) const
inlinenoexcept

Get the minimum number of features to extract for each model when building a classifier.

Returns
The minimum feature count.
Exceptions
Doesnot throw any exception.

◆ MinPairFeaturesDefault()

static int MinPairFeaturesDefault ( )
inlinestaticnoexcept

Default value for the MinPairFeatures.

Returns
Default min pair features value.
Exceptions
Doesnot throw any exception.

◆ NegativeDensity()

double NegativeDensity ( ) const
inlinenoexcept

Get the scan density with which to extract counter samples from the training set images.

Returns
The negative density value.
Exceptions
Doesnot throw any exception.

◆ NegativeDensityDefault()

static double NegativeDensityDefault ( )
inlinestaticnoexcept

Default value for the NegativeDensity.

Returns
Default negative density value.
Exceptions
Doesnot throw any exception.

◆ Polydromy()

int Polydromy ( ) const
inlinenoexcept

Get the polydromy value controlling the complexity of the feature search tree in the classifier.

Returns
The polydromy value.
Exceptions
Doesnot throw any exception.

◆ PolydromyDefault()

static int PolydromyDefault ( )
inlinestaticnoexcept

Default value for the Polydromy.

Returns
Default polydromy value.
Exceptions
Doesnot throw any exception.

◆ SetContrastTrigger()

void SetContrastTrigger ( int  contrastTrigger)
inline

Set the minimum contrast a Minos feature must achieve before it is eligible to become part of the classifier. Lower values will lead to a classifier that is more sensitive in low-contrast situation but might also increase the number of false positive results that need to be filtered out e.g. by means of their quality measure.

Parameters
[in]contrastTriggerThe contrast trigger value.
Exceptions
Anyexception derived from std::exception including CvbException.

◆ SetEnsembleSize()

void SetEnsembleSize ( int  ensembleSize)
inline

Set the maximum size of the Ensembles of similar instance images to be used for pair feature calculation. Valid ensemble sizes must be greater than 0, the default value is 15.

Parameters
[in]ensembleSizeThe ensemble size value.
Exceptions
Anyexception derived from std::exception including CvbException.

◆ SetIndifferenceRadius()

void SetIndifferenceRadius ( int  indifferenceRadius)
inline

Set the minimum distance to be assumed between a (labeled) positive sample and a counter sample in a training set image.

Parameters
[in]indifferenceRadiusThe indifference radius value.
Exceptions
Anyexception derived from std::exception including CvbException.

◆ SetMinPairFeatures()

void SetMinPairFeatures ( int  minPairFeatures)
inline

Set the minimum number of features to extract for each model when building a classifier.

Parameters
[in]minPairFeaturesThe minimum feature count.
Exceptions
Anyexception derived from std::exception including CvbException.

◆ SetNegativeDensity()

void SetNegativeDensity ( double  negativeDensity)
inline

Set the scan density with which to extract counter samples from the training set images. Higher densities will lead to a classifier that is potentially more robust versus false positive detections, but will also result in increased learning times.

Parameters
[in]negativeDensityThe negative density value.
Exceptions
Anyexception derived from std::exception including CvbException.

◆ SetPolydromy()

void SetPolydromy ( int  polydromy)
inline

Set the polydromy value controlling the complexity of the feature search tree in the classifier. Valid polydromy values must be greater than 0, the default value is 2.

Parameters
[in]polydromyThe polydromy value.
Exceptions
Anyexception derived from std::exception including CvbException.