org.openimaj.image.processing.face.detection

Class DetectedFace

java.lang.Object

org.openimaj.image.processing.face.detection.DetectedFace

All Implemented Interfaces:

ReadableBinary, ReadWriteableBinary, WriteableBinary

Direct Known Subclasses:

CCDetectedFace, CLMDetectedFace, EllipticalDetectedFace, KEDetectedFace, MultiTracker.TrackedFace

public class DetectedFace
extends Object
implements ReadWriteableBinary

A DetectedFace models a face detected by a face detector, together with the locations of certain facial features localised on the face.

Author:

Jonathon Hare

Field Summary

Fields

Modifier and Type	Field and Description
protected Rectangle	bounds The upright bounds of the face in the image in which it was detected
protected float	confidence The confidence of the detection; higher numbers mean higher confidence.
protected FImage	facePatch The extracted sub-image representing the face.

Constructor Summary

Constructors

Constructor and Description
DetectedFace() Default constructor with an empty rectangle as bounds
DetectedFace(Rectangle bounds, FImage patch, float confidence) Construct with a bounds rectangle (the bounding box of the face in the detection image) and an image patch that describes the contents of the bounds rectangle from the original image.

Method Summary

Modifier and Type	Method and Description
byte[]	binaryHeader() Header for binary input.
Rectangle	getBounds() Get the bounding box of the face in the detection image.
float	getConfidence() Get the confidence of the detection.
FImage	getFacePatch() Returns the sub-image representing the face.
Shape	getShape() Get the shape of the detection.
void	readBinary(DataInput in) Read internal state from in.
void	setBounds(Rectangle rect) Set the bounds of this face.
void	setConfidence(int confidence) Set the confidence of the detection.
void	setFacePatch(FImage img) Reset the face patch 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

Field Detail

bounds

protected Rectangle bounds

The upright bounds of the face in the image in which it was detected

facePatch

protected FImage facePatch

The extracted sub-image representing the face. This is normally extracted directly from the bounds rectangle in the original image, but in some cases might be extracted from a sub-region of the bounds rectangle.

confidence

protected float confidence

The confidence of the detection; higher numbers mean higher confidence.

Constructor Detail

DetectedFace

public DetectedFace()

Default constructor with an empty rectangle as bounds

DetectedFace

public DetectedFace(Rectangle bounds,
                    FImage patch,
                    float confidence)

Construct with a bounds rectangle (the bounding box of the face in the detection image) and an image patch that describes the contents of the bounds rectangle from the original image.

Parameters:

bounds - The bounding box of the face in the detection image.

patch - The subimage describing the contents of the bounding box.

confidence - The confidence of the detection.

Method Detail

getFacePatch

public FImage getFacePatch()

Returns the sub-image representing the face.

Returns:

Get the sub-image representing the detected face

setFacePatch

public void setFacePatch(FImage img)

Reset the face patch image

Parameters:

img - The image

getBounds

public Rectangle getBounds()

Get the bounding box of the face in the detection image. This might be the same as the shape returned by getShape(), or it might encompass that shape.

Returns:

The bounding box of the face in the detection image

setBounds

public void setBounds(Rectangle rect)

Set the bounds of this face. This is so that detected face objects can be updated if the bounds were inaccurate, or tracking is taking place on the object.

Parameters:

rect - The new bounds

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

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

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

getConfidence

public float getConfidence()

Get the confidence of the detection. Higher numbers mean higher confidence.

Returns:

the confidence.

getShape

public Shape getShape()

Get the shape of the detection. In most cases, this will just return the bounds rectangle, however, subclasses can override to return a better geometric description of the detection area.

Returns:

the shape describing the detection in the original image.

setConfidence

public void setConfidence(int confidence)

Set the confidence of the detection. Higher numbers mean higher confidence.

Parameters:

confidence - the confidence.