SearchPredictorFactory Class Reference

Factory class for the generation of search predictors. More...

Inherits PredictorFactoryBase.

Public Member Functions
	SearchPredictorFactory ()
	Ctor.
void	UseSettingsFromPredictor (SearchPredictor clf)
	Copy the predictor generation settings from a predictor.
SearchPredictor	TrainPredictor (SampleRegressionImageList sil)
	Create a regression predictor from a sample image list.
SearchPredictor	TrainPredictor (TrainingSet mts)
	Create a regression predictor from a Minos Training Set.
Public Member Functions inherited from PredictorFactoryBase
void	Dispose ()
	Disposes of the native data needed for marshalling.
void	UseSettingsFromPredictor (PredictorBase clf)
	Copy the classifier generation settings from a classifier.

Static Public Attributes
static readonly ValueRange< double >	ScaleFactorRangeDefault = new ValueRange<double>(1.0, 1.0)
	Default value for the scale factor range.
static readonly ValueRange< double >	SingularValueRangeDefault = new ValueRange<double>(1.0, 1.0)
	Default value for the singular value range.
static readonly ValueRange< double >	ScaleFactorRange = new ValueRange<double>(0.25, 10)
	Acceptable scale factor range for search classifier training.
const int	NumClassificationStepsMin = 3
	Minimum classification step count.
const int	SampleSizeMin = 1
	Absolute minimum value for SampleSize.
Static Public Attributes inherited from PredictorFactoryBase
static readonly ValueRange< double >	LambdaRange = new ValueRange<double>(0.0, 10.0)
	Acceptable scale factor range for search classifier training.
const double	LambdaDefault = 0.1
	Default value for lambda.
const int	FeatureResolutionDefault = 1
	Default value for feature resolution.
static readonly ValueRange< int >	FeatureResolutionRange = new ValueRange<int>(0, 10)
	Valid range of feature resolution value.
const int	PreprocessingMaxLength = InternalExtensions.PreprocessingMaxLength
	Maximum length of a preprocessing code (excluding the terminating zero).
const string	PreprocessingValidCharacters = InternalExtensions.PreprocessingValidCharacters
	characters that a preprocessing string may contain.

Properties
int	SampleSize [get, set]
	Sample size that has been used in each training set.
double	ExtractionRadius [get, set]
	Radius for extracting positive search instances. The unit size is the size of the feature window, i.e. a value of 0.5 means that positive samples can be extracted from withing a range of +/- Feature Window Width and +/- Feature Window Height around each trained instance. Smaller values will necessitate a finer search grid but may yield better results on difficult search tasks.
ValueRange< Angle >	AngleRange [get, set]
	Range of angles to be covered during classifier training.
ValueRange< double >	ScaleRange [get, set]
	Range of scale factors to be covered during classifier training. Only meaningful if the invariance type InvarianceType.RotationScaleTranslation has been set.
ValueRange< double >	SingularValueRange [get, set]
	Range of permissible singular values to be covered during classifier training. Only meaningful if the invariance type InvarianceType.AffineGroup has been set.
InvarianceType	Invariances [get, set]
	Invariances to be used for generating the classifier.
int	NumClassificationSteps [get, set]
	Number of classification steps during search operation.
int	FeatureResolutionStep1And2 [get, set]
	Feature resolution (determines the size of the classification retina) for search step 1 and 2.
int	FeatureResolutionRest [get, set]
	Feature resolution (determines the size of the classification retina) for step 3 and up.
Properties inherited from PredictorFactoryBase
double	Lambda [get, set]
	Regularization value to be used for generating the object. Possible values range from 0 to 10, good starting values for experiments are usually around 0.01.
string	Preprocessing [get, set]
	Preprocessing code with which the object is to be generated.

Additional Inherited Members
Static Public Member Functions inherited from PredictorFactoryBase
static string	FormatPreprocessingCode (string input)
	Correct a preprocessing code to make sure that no invalid characters are in the code and the code does not exceed the maximum length.
Protected Member Functions inherited from PredictorFactoryBase
	PredictorFactoryBase ()
	ctor (internal).
virtual void	Dispose (bool disposing)
	Clean-up of managed-to-native data structures.
virtual void	OnStartProgressReport (int id, string caption, int stepsTotal)
	Event raiser.
virtual void	OnProgressReport (int id, ref bool retval)
	Event raiser.
virtual void	OnEndProgressReport (int id)
	Event raiser.
Events inherited from PredictorFactoryBase
EventHandler< StartProgressReportEventArgs >	StartProgressReport
	Event that will be fired when a new progress stage was initiated.
EventHandler< ProgressReportEventArgs >	ProgressReport
	Event that informs about a progress step in the given stage.
EventHandler< EndProgressReportEventArgs >	EndProgressReport
	Event that informs about the finalization of a given stage.

Detailed Description

Factory class for the generation of search predictors.

Member Function Documentation

TrainPredictor() [1/2]

SearchPredictor TrainPredictor

(

SampleRegressionImageList

sil

)

Create a regression predictor from a sample image list.

Parameters

sil	Sample image list to train from.

Returns

Newly generated classifier.

Exceptions

PolimagoFactoryException

Training error (usually due to unsuitable parameters).

TrainPredictor() [2/2]

SearchPredictor TrainPredictor

(

TrainingSet

mts

)

Create a regression predictor from a Minos Training Set.

Parameters

mts	Training set to train from.

Returns

Newly generated classifier.

Exceptions

PolimagoFactoryException

Training error (usually due to unsuitable parameters).

UseSettingsFromPredictor()

void UseSettingsFromPredictor

(

SearchPredictor

clf

)

Copy the predictor generation settings from a predictor.

Parameters

clf	Classifier to take the settings from.