Package adams.data.image.imagesegmentationcontainer

Class EvaluatePrediction

java.lang.Object

adams.core.logging.LoggingObject

adams.core.logging.CustomLoggingLevelObject

adams.core.option.AbstractOptionHandler

adams.data.image.imagesegmentationcontainer.AbstractImageSegmentationContainerOperation

adams.data.image.imagesegmentationcontainer.EvaluatePrediction

All Implemented Interfaces:

Destroyable, GlobalInfoSupporter, LoggingLevelHandler, LoggingSupporter, OptionHandler, QuickInfoSupporter, SizeOfHandler, Serializable

public class EvaluatePrediction
extends AbstractImageSegmentationContainerOperation

Evaluates a prediction (first container) against the annotation (second container) and outputs a spreadsheet with the results.

Author:

FracPete (fracpete at waikato dot ac dot nz)

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field	Description
static String	KEY_ADDITIONAL	the key for additional count.
static String	KEY_ANNOTATION	the key for annotation count.
static String	KEY_MISSED	the key for missed count.
static String	KEY_OVERLAP	the key for overlap count.
protected boolean	m_AddMisclassification	whether to add misclassification information.

Fields inherited from class adams.core.option.AbstractOptionHandler

m_OptionManager

Fields inherited from class adams.core.logging.LoggingObject

m_Logger, m_LoggingIsEnabled, m_LoggingLevel

Constructor Summary

Constructors

Constructor	Description
EvaluatePrediction()

Method Summary

Modifier and Type	Method	Description
String	addMisclassificationTipText()	Returns the tip text for this property.
protected com.github.fracpete.javautils.struct.Struct2<Integer,Double>	calcMisclassified(int[] predPixels, int[] annoOtherPixels)	Calculates the misclassification count/percentage.
protected Map<String,Integer>	compare(int[] predPixels, int[] annoPixels)	Compares the two pixel arrays.
void	defineOptions()	Adds options to the internal list of options.
protected Object	doProcess(ImageSegmentationContainer[] containers)	Performs the actual processing of the containers.
Class	generates()	The type of data that is generated.
boolean	getAddMisclassification()	Returns whether to add the misclassification information.
String	getQuickInfo()	Returns a quick info about the actor, which will be displayed in the GUI.
String	globalInfo()	Returns a string describing the object.
int	maxNumContainersRequired()	Returns the maximum number of containers that are required for the operation.
int	minNumContainersRequired()	Returns the minimum number of containers that are required for the operation.
void	setAddMisclassification(boolean value)	Sets whether to add the misclassification information.

Methods inherited from class adams.data.image.imagesegmentationcontainer.AbstractImageSegmentationContainerOperation

check, checkSameDimensions, checkSameDimensions, process

Methods inherited from class adams.core.option.AbstractOptionHandler

cleanUpOptions, destroy, finishInit, getDefaultLoggingLevel, getOptionManager, initialize, loggingLevelTipText, newOptionManager, reset, setLoggingLevel, toCommandLine, toString

Methods inherited from class adams.core.logging.LoggingObject

configureLogger, getLogger, getLoggingLevel, initializeLogging, isLoggingEnabled, sizeOf

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Methods inherited from interface adams.core.logging.LoggingLevelHandler

getLoggingLevel

Field Detail

KEY_ANNOTATION

public static final String KEY_ANNOTATION

the key for annotation count.

See Also:

Constant Field Values

KEY_MISSED

public static final String KEY_MISSED

the key for missed count.

See Also:

Constant Field Values

KEY_OVERLAP

public static final String KEY_OVERLAP

the key for overlap count.

See Also:

Constant Field Values

KEY_ADDITIONAL

public static final String KEY_ADDITIONAL

the key for additional count.

See Also:

Constant Field Values

m_AddMisclassification

protected boolean m_AddMisclassification

whether to add misclassification information.

Constructor Detail

EvaluatePrediction

public EvaluatePrediction()

Method Detail

globalInfo

public String globalInfo()

Returns a string describing the object.

Specified by:

globalInfo in interface GlobalInfoSupporter

Specified by:

globalInfo in class AbstractOptionHandler

Returns:

a description suitable for displaying in the gui

defineOptions

public void defineOptions()

Adds options to the internal list of options.

Specified by:

defineOptions in interface OptionHandler

Overrides:

defineOptions in class AbstractOptionHandler

setAddMisclassification

public void setAddMisclassification(boolean value)

Sets whether to add the misclassification information.

Parameters:

value - true if to add

getAddMisclassification

public boolean getAddMisclassification()

Returns whether to add the misclassification information.

Returns:

true if to add

addMisclassificationTipText

public String addMisclassificationTipText()

Returns the tip text for this property.

Returns:

tip text for this property suitable for displaying in the GUI or for listing the options.

getQuickInfo

public String getQuickInfo()

Returns a quick info about the actor, which will be displayed in the GUI.

Specified by:

getQuickInfo in interface QuickInfoSupporter

Overrides:

getQuickInfo in class AbstractImageSegmentationContainerOperation

Returns:

null if no info available, otherwise short string

minNumContainersRequired

public int minNumContainersRequired()

Returns the minimum number of containers that are required for the operation.

Specified by:

minNumContainersRequired in class AbstractImageSegmentationContainerOperation

Returns:

the number of containers that are required, <= 0 means no lower limit

maxNumContainersRequired

public int maxNumContainersRequired()

Returns the maximum number of containers that are required for the operation.

Specified by:

maxNumContainersRequired in class AbstractImageSegmentationContainerOperation

Returns:

the number of containers that are required, <= 0 means no upper limit

generates

public Class generates()

The type of data that is generated.

Specified by:

generates in class AbstractImageSegmentationContainerOperation

Returns:

the class

compare

protected Map<String,Integer> compare(int[] predPixels,
                                            int[] annoPixels)

Compares the two pixel arrays.

Parameters:

predPixels - the prediction pixels

annoPixels - the annotation pixels

Returns:

the statistics

calcMisclassified

protected com.github.fracpete.javautils.struct.Struct2<Integer,Double> calcMisclassified(int[] predPixels,
                                                                                               int[] annoOtherPixels)

Calculates the misclassification count/percentage. Percentage is calculated as: miscl_pixel_count / total_pixel_count_other_label

Parameters:

predPixels - the prediction pixels

annoOtherPixels - the annotation pixels from another layer

Returns:

the misclassified pixel count and percentage

doProcess

protected Object doProcess(ImageSegmentationContainer[] containers)

Performs the actual processing of the containers.

Specified by:

doProcess in class AbstractImageSegmentationContainerOperation

Parameters:

containers - the containers to process

Returns:

the generated data