TrainingSet.ModelInfo Class Reference

InstanceInformation that has been added to a training set. More...

Inherits TrainingSet.TrainingSetObject.

Public Member Functions
override bool	Equals (object obj)
	Compare a ModelInformation object versus anything else. More...
unsafe override int	GetHashCode ()
	Build a sensible hash value from the native handle. More...
unsafe SearchResult[]	CheckConsistency (ImageInfo trainingSetImage, double threshold, double density)
	Test the image referenced by trainingSetImage for instances of this model that might have been forgotten during the training process. More...
unsafe SearchResult[]	CheckConsistency (double threshold, double density)
	Test all images in the parent training set for instances of this model that might have been forgotten during the training process. More...
void	GetMaxFeatureWindow (out int left, out int top, out int right, out int bottom)
	Retrieve the maximum values that may be set as feature window for this model. The maximum range is calculated based on the actual locations of the model's instances inside the training set images (i.e. on their distance to the image borders...). The minimum value in each direction is of course 0. More...
Rect	GetMaxFeatureWindow ()
	Retrieve the maximum values that may be set as feature window for this model. The maximum range is calculated based on the actual locations of the model's instances inside the training set images (i.e. on their distance to the image borders...). The minimum value in each direction is of course 0. More...
Rect	GetExtractableArea (ImageInfo img)
	Determine the maximum area from which an instance of this model may be extracted from a given training set image. More...

Static Public Member Functions
static bool	operator== (ModelInfo lhs, ModelInfo rhs)
	Comparison operator for instance information objects. More...
static bool	operator!= (ModelInfo lhs, ModelInfo rhs)
	Comparison operator for instance information objects. More...

Protected Member Functions
override int	GetIndex ()
	Index of this MTS instance inside the training set More...
override Image	CreateImageRepresentation ()
	Creates the image used for representing this object. More...
abstract int	GetIndex ()
	Method through which the inherited classes retrieve the index this object has in its "master" collection underneath the TrainingSet. More...
abstract Image	CreateImageRepresentation ()
	Creates the image used for representing this object. More...

Properties
unsafe string	Name [get, set]
	Gets or sets the name of the model. More...
Point2Dd	AdvanceVector [get, set]
	Advance vector associated with this model. More...
Rect	FeatureWindow [get, set]
	Gets or sets the feature window for a Minos Training Set model. More...
Point2Dd	Origin [get, set]
	Gets or sets the origin of the model in terms of coordinates inside the feature window More...
ModelInstanceInfoCollection	Instances [get]
	The instances belonging to this model. More...
Properties inherited from TrainingSet.TrainingSetObject
int	Index [get]
	Index of this object in the parent's collection. More...
Image	Image [get]
	Image representation of this object. More...

Additional Inherited Members
Protected Attributes inherited from TrainingSet.TrainingSetObject
readonly IntPtr	collectionParent_
	Native handle to the parent of the collection (which is not necessarily the training set!)

Detailed Description

InstanceInformation that has been added to a training set.

Member Function Documentation

CheckConsistency() [1/2]

unsafe SearchResult[] CheckConsistency	(	double	threshold,
		double	density
	)

Test all images in the parent training set for instances of this model that might have been forgotten during the training process.

Parameters

threshold	correlation threshold to be used for the consistency check
density	density to be used for the consistency check

Returns

potentially forgotten positive samples that may be added to the training set

Exceptions

ObjectDisposedException	If the training set has already been disposed
ArgumentOutOfRangeException	If invalid values for threshold or density have been passed (both parameters must be within the range [0...1.0]
CvbException	If the execution of the consistency check failed

CheckConsistency() [2/2]

unsafe SearchResult[] CheckConsistency	(	ImageInfo	trainingSetImage,
		double	threshold,
		double	density
	)

Test the image referenced by trainingSetImage for instances of this model that might have been forgotten during the training process.

Parameters

threshold	correlation threshold to be used for the consistency check
density	density to be used for the consistency check
trainingSetImage	training set image on which to perform the consistency check

Returns

potentially forgotten positive samples that may be added to the training set

Exceptions

ObjectDisposedException	If the training set has already been disposed
ArgumentOutOfRangeException	If invalid values for threshold or density have been passed (both parameters must be within the range [0...1.0]
ArgumentNullException	If the trainingSetImage argument was null
CvbException	If the execution of the consistency check failed

CreateImageRepresentation()

override Image CreateImageRepresentation ( )

protectedvirtual

Creates the image used for representing this object.

Returns

Image representing this object.

Implements TrainingSet.TrainingSetObject.

Equals()

override bool Equals

(

object

obj

)

Compare a ModelInformation object versus anything else.

Parameters

obj	Object to compare to.

Returns

Comparison result.

GetExtractableArea()

Rect GetExtractableArea

(

ImageInfo

img

)

Determine the maximum area from which an instance of this model may be extracted from a given training set image.

Parameters

img	Training set image for which to query the extractable area.

Returns

Extractable area.

Exceptions

NullReferenceException	If the input image is null
ObjectDisposedException	If the input image or the parent Training Set has already been disposed.

GetHashCode()

unsafe override int GetHashCode

(

)

Build a sensible hash value from the native handle.

Returns

The hash code for this object.

GetIndex()

override int GetIndex ( )

protectedvirtual

Index of this MTS instance inside the training set

Returns

index

Implements TrainingSet.TrainingSetObject.

GetMaxFeatureWindow() [1/2]

Rect GetMaxFeatureWindow

(

)

Retrieve the maximum values that may be set as feature window for this model. The maximum range is calculated based on the actual locations of the model's instances inside the training set images (i.e. on their distance to the image borders...). The minimum value in each direction is of course 0.

Returns

Maximum feature window extent.

GetMaxFeatureWindow() [2/2]

void GetMaxFeatureWindow	(	out int	left,
		out int	top,
		out int	right,
		out int	bottom
	)

Retrieve the maximum values that may be set as feature window for this model. The maximum range is calculated based on the actual locations of the model's instances inside the training set images (i.e. on their distance to the image borders...). The minimum value in each direction is of course 0.

Parameters

left	maximum possible value for the left edge of the feature window
top	maximum possible value for the top edge of the feature window
right	maximum possible value for the right edge of the feature window
bottom	maximum possilbe value for the bottom edge of the feature window

operator!=()

static bool operator!= ( ModelInfo  lhs, ModelInfo  rhs  )

static

Comparison operator for instance information objects.

Parameters

lhs	object to compare
rhs	object to compare

Returns

false if the two objects refer to the same instance

operator==()

static bool operator== ( ModelInfo  lhs, ModelInfo  rhs  )

static

Comparison operator for instance information objects.

Parameters

lhs	object to compare
rhs	object to compare

Returns

true if the two objects refer to the same instance

Property Documentation

AdvanceVector

Point2Dd AdvanceVector

getset

Advance vector associated with this model.

Exceptions

ObjectDisposedException

If the training set has already been disposed

FeatureWindow

Rect FeatureWindow

getset

Gets or sets the feature window for a Minos Training Set model.

Exceptions

ObjectDisposedException	If the training set has already been disposed
ArgumentException	when trying to set a feature window that is not compatible with the geometry of the already trained models and the training set images

Instances

ModelInstanceInfoCollection Instances

get

The instances belonging to this model.

Exceptions

ObjectDisposedException

If the training set has already been disposed

Name

unsafe string Name

getset

Gets or sets the name of the model.

Note that model names are not required to be unique for Minos! However, if you give two models the same name, there will be no way to determine to which specific model of a class with more than one model a result reported by a Minos classifier belongs.

Exceptions

ObjectDisposedException	If the training set has already been disposed
ArgumentNullException	when trying to set a null string
ArgumentException	when trying to set an empty string or if the string contains an unmappable unicode character

Origin

Point2Dd Origin

getset

Gets or sets the origin of the model in terms of coordinates inside the feature window

Exceptions

ObjectDisposedException

If the training set has already been disposed