Manto classifier object. More...

Inherits INativeHandle.

Classes
struct	ClassInformation
	Information about one of the classes in a Classifier. More...

class	ClassInformationCollection
	Collection for classifier-based class information. Classifier-based class information is a bit more scarce because it lacks the sample list. More...

Public Member Functions
	Classifier (string fileName)
	Constructor that loads a classifier from a file More...

void	Dispose ()
	Dispose method that releases the classifier

void	Save (string fileName)
	Save the classifier to a file. More...

SearchResult[]	SearchAll (Image image, Rect aoi, bool useVote, double minConfidence, int locality, int granularity)
	Search for all occurrences of a known class in an image. More...

SearchResult[]	SearchAll (Image image, Rect aoi, bool useVote, double minConfidence, int locality)
	Search for all occurrences of a known class in an image. More...

SearchResult	Search (Image image, Rect aoi, bool useVote, double minConfidence, out Image accumulator)
	Search for the result with the highest confidence. More...

SearchResult	Search (Image image, Rect aoi, bool useVote, double minConfidence)
	Search for the result with the highest confidence. More...

Protected Member Functions
virtual void	Dispose (bool disposing)
	IDispose helper function. More...

Properties
IntPtr	Handle `[get]`
	Native Manto classifier handle. More...

bool	IsDisposed `[get]`
	Tests if the native handle has already been disposed.

string	FileName `[get]`
	Name of the file from which this image list was loaded (string.Empty if this image list was neither loaded nor saved since its construction). More...

ClassInformationCollection	Classes `[get]`
	Collection of classes in this classifier. More...

string	PreprocessingCode `[get]`
	Retrieves the preprocessing code that has been used for generating this Manto classifier. More...

string	Comment `[get, set]`
	Textual comment for the classifier. More...

Size2D	FeatureWindowSize `[get]`
	Size of the classifier's feature window. More...

int	FeatureWindowDimension `[get]`
	Dimension of the classifier's feature window. More...

Point2D	FeatureWindowOrigin `[get]`
	Dimension of the classifier's feature window. More...

int	ExcludedClassIndex `[get, set]`
	index of the currently excluded class. More...

DecisionBoundary	DecisionBoundary `[get]`
	Decision boundary setting that has been used for classifier generation. More...

Properties inherited from INativeHandle
IntPtr	Handle `[get]`
	The native handle of the object.

bool	IsDisposed `[get]`
	Possibility to check whether the object has already been disposed of.

Events
NativeHandleEventDelegate	ObjectDisposing
	Raised when this object is about to be disposed via the IDisposable.Dispose method. More...

Events inherited from INativeHandle
NativeHandleEventDelegate	ObjectDisposing
	Raised when this object is about to be disposed via the IDisposable.Dispose method. More...

Detailed Description

Manto classifier object.

Constructor & Destructor Documentation

◆ Classifier()

Classifier ( string fileName )

Constructor that loads a classifier from a file

Parameters

fileName file from which to load the classifier

Exceptions

FileNotFoundException	when the file specified by the fileName parameter does not exist
FileLoadException	If the file specified by the fileName parameter exists, but cannot be loaded
ArgumentNullException	If fileName is null

Member Function Documentation

◆ Dispose()

virtual void Dispose ( bool disposing )

protectedvirtual

IDispose helper function.

Parameters

disposing true when called via IDisposable.Dispose, false when called by the finalizer.

◆ Save()

void Save ( string fileName )

Save the classifier to a file.

Parameters

fileName file to which to save

Exceptions

ObjectDisposedException	If the classifier has already been disposed
ArgumentNullException	If the fileName parameter is null
IOException	If saving the classifier failed

◆ Search() [1/2]

SearchResult Search	(	Image	image,
		Rect	aoi,
		bool	useVote,
		double	minConfidence
	)

Search for the result with the highest confidence.

Parameters

image	image in which to search
aoi	region of the image in which to search
useVote	switch voting on or off (voting is a parameter that can allow for more precise class assignment when set to true, but setting voting to true will significantly increase the processing time)
minConfidence	minimum confidence for the results to be reported; must not exceed the range [0...1]

Returns: search result (SearchResult.Empty if nothing was found)

Exceptions

ObjectDisposedException	If this classifier or the image has already been disposed
ArgumentOutOfRangeException	If the minConfidence parameter exceeds the range [0..1]

◆ Search() [2/2]

SearchResult Search	(	Image	image,
		Rect	aoi,
		bool	useVote,
		double	minConfidence,
		out Image	accumulator
	)

Search for the result with the highest confidence.

Parameters

image	image in which to search
aoi	region of the image in which to search
useVote	switch voting on or off (voting is a parameter that can allow for more precise class assignment when set to true, but setting voting to true will significantly increase the processing time)
minConfidence	minimum confidence for the results to be reported; must not exceed the range [0...1]
accumulator	returns the accumulator built during the search operation; the accumulator may be useful for further result investigation

Returns: search result (SearchResult.Empty if nothing was found)

Exceptions

ObjectDisposedException	If this classifier or the image has already been disposed
ArgumentOutOfRangeException	If the minConfidence parameter exceeds the range [0..1]
ArgumentException	If the image is incompatible with the classifier or the aoi cannot hold one of the classifier's classes.

◆ SearchAll() [1/2]

SearchResult[] SearchAll	(	Image	image,
		Rect	aoi,
		bool	useVote,
		double	minConfidence,
		int	locality
	)

Search for all occurrences of a known class in an image.

Parameters

image	image in which to search
aoi	region of the image in which to search
useVote	switch voting on or off (voting is a parameter that can allow for more precise class assignment when set to true, but setting voting to true will significantly increase the processing time)
minConfidence	minimum confidence for the results to be reported; must not exceed the range [0...1]
locality	separation of the search results in pixels (no two results should be closer to each other than the distance specified here)

Returns: list of found results; might be empty if nothing was found, null if the search call failed

Exceptions

ObjectDisposedException	If this classifier or the image has already been disposed
ArgumentOutOfRangeException	If the minConfidence parameter exceeds the range [0..1]

◆ SearchAll() [2/2]

SearchResult[] SearchAll	(	Image	image,
		Rect	aoi,
		bool	useVote,
		double	minConfidence,
		int	locality,
		int	granularity
	)

Search for all occurrences of a known class in an image.

Parameters

image	image in which to search
aoi	region of the image in which to search
useVote	switch voting on or off (voting is a parameter that can allow for more precise class assignment when set to true, but setting voting to true will significantly increase the processing time)
minConfidence	minimum confidence for the results to be reported; must not exceed the range [0...1]
locality	separation of the search results in pixels (no two results should be closer to each other than the distance specified here)
granularity	the granularity parameter may be used to simulate a shorter or longer preprocessing code, making the grid of points to be calculated for classification denser or thinner; -1 indicates that the default value should be used; note that the granularity parameter can have a huge impact on processing time - it is generally not recommended to use parameters other than -1

Returns: list of found results; might be empty if nothing was found, null if the search call failed

Exceptions

ObjectDisposedException	If this classifier or the image has already been disposed
ArgumentOutOfRangeException	If the minConfidence parameter exceeds the range [0..1]
ArgumentException	If the image is incompatible with the classifier or the aoi cannot hold one of the classifier's classes.

Property Documentation

◆ Classes

ClassInformationCollection Classes

get

Collection of classes in this classifier.

Exceptions

ObjectDisposedException If the classifier has already been disposed

◆ Comment

string Comment

getset

Textual comment for the classifier.

Exceptions

ObjectDisposedException If the classifier has already been disposed

◆ DecisionBoundary

DecisionBoundary DecisionBoundary

get

Decision boundary setting that has been used for classifier generation.

Exceptions

ObjectDisposedException If the image list has already been disposed

◆ ExcludedClassIndex

int ExcludedClassIndex

getset

index of the currently excluded class.

Exceptions

ObjectDisposedException	If the classifier has already been disposed
ArgumentOutOfRangeException	If the class index is out of range.

◆ FeatureWindowDimension

int FeatureWindowDimension

get

Dimension of the classifier's feature window.

Exceptions

ObjectDisposedException If the classifier has already been disposed

◆ FeatureWindowOrigin

Point2D FeatureWindowOrigin

get

Dimension of the classifier's feature window.

Exceptions

ObjectDisposedException If the classifier has already been disposed

◆ FeatureWindowSize

Size2D FeatureWindowSize

get

Size of the classifier's feature window.

Exceptions

ObjectDisposedException If the classifier has already been disposed

◆ FileName

string FileName

get

Name of the file from which this image list was loaded (string.Empty if this image list was neither loaded nor saved since its construction).

Exceptions

ObjectDisposedException If the classifier has already been disposed

◆ Handle

IntPtr Handle

get

Native Manto classifier handle.

It is normally not necessary to work with this handle in CVB.Net. Note that using this handle in connection with the legacy CVB managed wrappers may actually be disruptive to your application.

Implements INativeHandle.

◆ PreprocessingCode

string PreprocessingCode

get

Retrieves the preprocessing code that has been used for generating this Manto classifier.

Exceptions

ObjectDisposedException If the classifier has already been disposed

Event Documentation

◆ ObjectDisposing

NativeHandleEventDelegate ObjectDisposing

Raised when this object is about to be disposed via the IDisposable.Dispose method.

This event is raised right before this object is disposed. The dispose itself cannot be canceled.

Classes

Public Member Functions

Protected Member Functions

Properties

Events

Detailed Description

Constructor & Destructor Documentation

◆ Classifier()

Member Function Documentation

◆ Dispose()

◆ Save()

◆ Search() [1/2]

◆ Search() [2/2]

◆ SearchAll() [1/2]

◆ SearchAll() [2/2]

Property Documentation

◆ Classes

◆ Comment

◆ DecisionBoundary

◆ ExcludedClassIndex

◆ FeatureWindowDimension

◆ FeatureWindowOrigin

◆ FeatureWindowSize

◆ FileName

◆ Handle

◆ PreprocessingCode

Event Documentation

◆ ObjectDisposing