org.openimaj.image.processing.face.feature

Class FisherFaceFeature.Extractor<T extends DetectedFace>

java.lang.Object

org.openimaj.image.processing.face.feature.FisherFaceFeature.Extractor<T>

Type Parameters:

T -

All Implemented Interfaces:

FeatureExtractor<FisherFaceFeature,T>, FacialFeatureExtractor<FisherFaceFeature,T>, ReadableBinary, ReadWriteableBinary, WriteableBinary, BatchTrainer<IndependentPair<?,T>>

Enclosing class:

FisherFaceFeature

public static class FisherFaceFeature.Extractor<T extends DetectedFace>
extends Object
implements FacialFeatureExtractor<FisherFaceFeature,T>, BatchTrainer<IndependentPair<?,T>>

A FacialFeatureExtractor for producing FisherFaces. Unlike most FacialFeatureExtractors, this one either needs to be trained or provided with a pre-trained FisherImages object.

A FaceAligner can be used to produce aligned faces for training and feature extraction.

Author:

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

Constructor Summary

Constructors

Constructor and Description
Extractor(FisherImages basis, FaceAligner<T> aligner) Construct with given pre-trained FisherImages basis and a face aligner.
Extractor(int numComponents, FaceAligner<T> aligner) Construct with the requested number of components (the number of PCs to keep) and a face aligner.

Method Summary

Modifier and Type	Method and Description
byte[]	binaryHeader() Header for binary input.
FisherFaceFeature	extractFeature(T face) Extract features from an object and return them.
void	readBinary(DataInput in) Read internal state from in.
<KEY> void	train(GroupedDataset<KEY,? extends ListDataset<T>,T> data) Train on a grouped dataset.
void	train(List<? extends IndependentPair<?,T>> data) Train the object with the given data.
void	train(Map<?,? extends List<T>> data) Train on a map of data.
void	writeBinary(DataOutput out) Write the content of this as binary to out.

Methods inherited from class java.lang.Object

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

Constructor Detail

Extractor

public Extractor(int numComponents,
                 FaceAligner<T> aligner)

Construct with the requested number of components (the number of PCs to keep) and a face aligner. The principal components must be learned by calling train(List).

Parameters:

numComponents - the number of principal components to keep.

aligner - the face aligner

Extractor

public Extractor(FisherImages basis,
                 FaceAligner<T> aligner)

Construct with given pre-trained FisherImages basis and a face aligner.

Parameters:

basis - the pre-trained basis

aligner - the face aligner

Method Detail

extractFeature

public FisherFaceFeature extractFeature(T face)

Description copied from interface: FeatureExtractor

Extract features from an object and return them.

Specified by:

extractFeature in interface FeatureExtractor<FisherFaceFeature,T extends DetectedFace>

Parameters:

face - the object to extract from

Returns:

the extracted feature

readBinary

public void readBinary(DataInput in)
                throws IOException

Description copied from interface: ReadableBinary

Read internal state from in.

Specified by:

readBinary in interface ReadableBinary

Parameters:

in - source to read from.

Throws:

IOException - an error reading input

binaryHeader

public byte[] binaryHeader()

Description copied from interface: ReadableBinary

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

Specified by:

binaryHeader in interface ReadableBinary

Specified by:

binaryHeader in interface WriteableBinary

Returns:

header

writeBinary

public void writeBinary(DataOutput out)
                 throws IOException

Description copied from interface: WriteableBinary

Write the content of this as binary to out.

Specified by:

writeBinary in interface WriteableBinary

Parameters:

out - sink to write to

Throws:

IOException - an error writing to out

train

public void train(List<? extends IndependentPair<?,T>> data)

Description copied from interface: BatchTrainer

Train the object with the given data. BatchTrainers should reset the underlying model everytime this method is called.

Specified by:

train in interface BatchTrainer<IndependentPair<?,T extends DetectedFace>>

Parameters:

data - the training data

train

public void train(Map<?,? extends List<T>> data)

Train on a map of data.

Parameters:

data - the data

train

public <KEY> void train(GroupedDataset<KEY,? extends ListDataset<T>,T> data)

Train on a grouped dataset.

Type Parameters:

KEY - The group type

Parameters:

data - the data