org.openimaj.image.model

Class FisherImages

java.lang.Object

org.openimaj.image.model.FisherImages

All Implemented Interfaces:

FeatureExtractor<DoubleFV,FImage>, ReadableBinary, ReadWriteableBinary, WriteableBinary, BatchTrainer<IndependentPair<?,FImage>>

@Reference(type=Article,
           author={"Belhumeur, Peter N.","Hespanha, Jo\\~{a}o P.","Kriegman, David J."},
           title="Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection",
           year="1997",
           journal="IEEE Trans. Pattern Anal. Mach. Intell.",
           pages={"711","","720"},
           url="http://dx.doi.org/10.1109/34.598228",
           month="July",
           number="7",
           publisher="IEEE Computer Society",
           volume="19",
           customData={"issn","0162-8828","numpages","10","doi","10.1109/34.598228","acmid","261512","address","Washington, DC, USA","keywords","Appearance-based vision, face recognition, illumination invariance, Fisher\'s linear discriminant."})
public class FisherImages
extends Object
implements BatchTrainer<IndependentPair<?,FImage>>, FeatureExtractor<DoubleFV,FImage>, ReadWriteableBinary

Implementation of Fisher Images (aka "FisherFaces"). PCA is used to avoid the singular within-class scatter matrix.

Author:

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

Constructor Summary

Constructors

Constructor and Description
FisherImages(int numComponents) Construct with the given number of components.

Method Summary

Modifier and Type	Method and Description
byte[]	binaryHeader() Header for binary input.
DoubleFV	extractFeature(FImage object) Extract features from an object and return them.
double[]	getBasisVector(int index) Get a specific basis vector as a double array.
void	readBinary(DataInput in) Read internal state from in.
<KEY> void	train(GroupedDataset<KEY,? extends ListDataset<FImage>,FImage> data) Train on a grouped dataset.
void	train(List<? extends IndependentPair<?,FImage>> data) Train the object with the given data.
void	train(Map<?,? extends List<FImage>> data) Train on a map of data.
FImage	visualise(int num) Draw an eigenvector as an image
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

FisherImages

public FisherImages(int numComponents)

Construct with the given number of components.

Parameters:

numComponents - the number of components

Method Detail

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(Map<?,? extends List<FImage>> data)

Train on a map of data.

Parameters:

data - the data

train

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

Train on a grouped dataset.

Type Parameters:

KEY - The group type

Parameters:

data - the data

train

public void train(List<? extends IndependentPair<?,FImage>> 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<?,FImage>>

Parameters:

data - the training data

extractFeature

public DoubleFV extractFeature(FImage object)

Description copied from interface: FeatureExtractor

Extract features from an object and return them.

Specified by:

extractFeature in interface FeatureExtractor<DoubleFV,FImage>

Parameters:

object - the object to extract from

Returns:

the extracted feature

getBasisVector

public double[] getBasisVector(int index)

Get a specific basis vector as a double array. The returned array contains a copy of the data.

Parameters:

index - the index of the vector

Returns:

the eigenvector

visualise

public FImage visualise(int num)

Draw an eigenvector as an image

Parameters:

num - the index of the eigenvector to draw.

Returns:

an image showing the eigenvector.