org.openimaj.image.processing.face.recognition

Class FisherFaceRecogniser<FACE extends DetectedFace,PERSON>

java.lang.Object

org.openimaj.ml.annotation.AbstractAnnotator<OBJECT,ANNOTATION>

org.openimaj.ml.annotation.IncrementalAnnotator<FACE,PERSON>

org.openimaj.image.processing.face.recognition.FaceRecogniser<FACE,PERSON>

org.openimaj.image.processing.face.recognition.FisherFaceRecogniser<FACE,PERSON>

Type Parameters:

FACE - Type of DetectedFace

PERSON - Type of object representing a person

All Implemented Interfaces:

Classifier<PERSON,FACE>, ReadableBinary, ReadWriteableBinary, WriteableBinary, Annotator<FACE,PERSON>, RestrictedAnnotator<FACE,PERSON>, IncrementalTrainer<Annotated<FACE,PERSON>>

public class FisherFaceRecogniser<FACE extends DetectedFace,PERSON>
extends FaceRecogniser<FACE,PERSON>

Implementation of a FaceRecogniser based on Fisherfaces. Any kind of machine learning implementation can be used for the actual classification.

Author:

Jonathon Hare (jsh2@ecs.soton.ac.uk)

Constructor Summary

Constructors

Modifier	Constructor and Description
protected	FisherFaceRecogniser()
	FisherFaceRecogniser(FisherFaceFeature.Extractor<FACE> extractor, FaceRecogniser<FACE,PERSON> internalRecogniser) Construct with the given feature extractor and underlying FaceRecogniser.
	FisherFaceRecogniser(FisherFaceFeature.Extractor<FACE> extractor, IncrementalAnnotator<FACE,PERSON> annotator) Construct with the given feature extractor and underlying IncrementalAnnotator.

Method Summary

Modifier and Type	Method and Description
List<ScoredAnnotation<PERSON>>	annotate(FACE object) Attempt to recognize the given face.
List<ScoredAnnotation<PERSON>>	annotate(FACE object, Collection<PERSON> restrict) Attempt to recognize the given face, restricting the potential people to coming from the given set.
protected void	beforeBatchTrain(GroupedDataset<PERSON,ListDataset<FACE>,FACE> dataset) Called before batch training/re-training takes place.
byte[]	binaryHeader() Header for binary input.
static <FACE extends DetectedFace,PERSON> FisherFaceRecogniser<FACE,PERSON>	create(int numComponents, FaceAligner<FACE> aligner, int k, DoubleFVComparator compar) Convenience method to create an FisherFaceRecogniser with a standard KNN classifier.
static <FACE extends DetectedFace,PERSON> FisherFaceRecogniser<FACE,PERSON>	create(int numComponents, FaceAligner<FACE> aligner, int k, DoubleFVComparator compar, float threshold) Convenience method to create an FisherFaceRecogniser with a standard KNN classifier, incorporating a threshold on the maximum distance (or minimum similarity) to allow a match.
Set<PERSON>	getAnnotations()
void	readBinary(DataInput in) Read internal state from in.
void	reset() Reset the object to its initial condition, as if it hasn't seen any training data.
String	toString()
void	train(Annotated<FACE,PERSON> annotated) Train/update object using a new instance.
void	writeBinary(DataOutput out) Write the content of this as binary to out.

Methods inherited from class org.openimaj.image.processing.face.recognition.FaceRecogniser

annotateBest, annotateBest, listPeople

Methods inherited from class org.openimaj.ml.annotation.IncrementalAnnotator

train, train, trainMultiClass

Methods inherited from class org.openimaj.ml.annotation.AbstractAnnotator

classify

Methods inherited from class java.lang.Object

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

Constructor Detail

FisherFaceRecogniser

protected FisherFaceRecogniser()

FisherFaceRecogniser

public FisherFaceRecogniser(FisherFaceFeature.Extractor<FACE> extractor,
                            FaceRecogniser<FACE,PERSON> internalRecogniser)

Construct with the given feature extractor and underlying FaceRecogniser.

Parameters:

extractor - the feature extractor

internalRecogniser - the face recogniser

FisherFaceRecogniser

public FisherFaceRecogniser(FisherFaceFeature.Extractor<FACE> extractor,
                            IncrementalAnnotator<FACE,PERSON> annotator)

Construct with the given feature extractor and underlying IncrementalAnnotator.

Parameters:

extractor - the feature extractor

annotator - the annotator

Method Detail

create

public static <FACE extends DetectedFace,PERSON> FisherFaceRecogniser<FACE,PERSON> create(int numComponents,
                                                                                          FaceAligner<FACE> aligner,
                                                                                          int k,
                                                                                          DoubleFVComparator compar)

Convenience method to create an FisherFaceRecogniser with a standard KNN classifier.

Type Parameters:

FACE - The type of DetectedFace

PERSON - the type representing a person

Parameters:

numComponents - the number of principal components to keep

aligner - the face aligner

k - the number of nearest neighbours

compar - the distance comparison function

Returns:

a new FisherFaceRecogniser

create

public static <FACE extends DetectedFace,PERSON> FisherFaceRecogniser<FACE,PERSON> create(int numComponents,
                                                                                          FaceAligner<FACE> aligner,
                                                                                          int k,
                                                                                          DoubleFVComparator compar,
                                                                                          float threshold)

Convenience method to create an FisherFaceRecogniser with a standard KNN classifier, incorporating a threshold on the maximum distance (or minimum similarity) to allow a match.

Type Parameters:

FACE - The type of DetectedFace

PERSON - the type representing a person

Parameters:

numComponents - the number of principal components to keep

aligner - the face aligner

k - the number of nearest neighbours

compar - the distance comparison function

threshold - a distance threshold to limit matches.

Returns:

a new FisherFaceRecogniser

beforeBatchTrain

protected void beforeBatchTrain(GroupedDataset<PERSON,ListDataset<FACE>,FACE> dataset)

Called before batch training/re-training takes place.

Parameters:

dataset - the dataset

toString

public String toString()

Overrides:

toString in class Object

readBinary

public void readBinary(DataInput in)
                throws IOException

Description copied from interface: ReadableBinary

Read internal state from in.

Parameters:

in - source to read from.

Throws:

IOException - an error reading input

writeBinary

public void writeBinary(DataOutput out)
                 throws IOException

Description copied from interface: WriteableBinary

Write the content of this as binary to out.

Parameters:

out - sink to write to

Throws:

IOException - an error writing to out

binaryHeader

public byte[] binaryHeader()

Description copied from interface: ReadableBinary

Header for binary input. Will be automatically read by IOUtils when using readBinary().

Returns:

header

train

public void train(Annotated<FACE,PERSON> annotated)

Description copied from interface: IncrementalTrainer

Train/update object using a new instance.

Parameters:

annotated - instance to train with

reset

public void reset()

Description copied from interface: IncrementalTrainer

Reset the object to its initial condition, as if it hasn't seen any training data.

getAnnotations

public Set<PERSON> getAnnotations()

Returns:

a Set of all annotations this Annotator knows about

annotate

public List<ScoredAnnotation<PERSON>> annotate(FACE object,
                                               Collection<PERSON> restrict)

Description copied from class: FaceRecogniser

Attempt to recognize the given face, restricting the potential people to coming from the given set.

Specified by:

annotate in interface RestrictedAnnotator<FACE extends DetectedFace,PERSON>

Specified by:

annotate in class FaceRecogniser<FACE extends DetectedFace,PERSON>

Parameters:

object - the detected face

restrict - the set of allowed people

Returns:

potential people

annotate

public List<ScoredAnnotation<PERSON>> annotate(FACE object)

Description copied from class: FaceRecogniser

Attempt to recognize the given face.

Specified by:

annotate in interface Annotator<FACE extends DetectedFace,PERSON>

Specified by:

annotate in class FaceRecogniser<FACE extends DetectedFace,PERSON>

Parameters:

object - the detected face

Returns:

potential people