org.openimaj.image.model.landmark

Class FNormalLandmarkModel

java.lang.Object

org.openimaj.image.model.landmark.FNormalLandmarkModel

All Implemented Interfaces:

LandmarkModel<FImage>

public class FNormalLandmarkModel
extends Object
implements LandmarkModel<FImage>

An FNormalLandmarkModel is a landmark represented by the surface normal line of a point (which is usually part of a PointList in an FImage connected by PointListConnections).

Author:

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

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	FNormalLandmarkModel.Factory A factory for producing FNormalLandmarkModels

Constructor Summary

Constructors

Constructor and Description
FNormalLandmarkModel(PointListConnections connections, FLineSampler sampler, int numModelSamples, int numSearchSamples, float normalLength) Default constructor.

Method Summary

Modifier and Type	Method and Description
float	computeCost(FImage image, Point2d point, PointList pointList) Evaluate the cost function using the given image and point.
void	updateModel(FImage image, Point2d point, PointList pointList) Update the internal model of local image content by adding information from the provided image.
ObjectFloatPair<Point2d>	updatePosition(FImage image, Point2d initial, PointList pointList) Estimate an improved fit based on a local neighbourhood search.

Methods inherited from class java.lang.Object

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

Constructor Detail

FNormalLandmarkModel

public FNormalLandmarkModel(PointListConnections connections,
                            FLineSampler sampler,
                            int numModelSamples,
                            int numSearchSamples,
                            float normalLength)

Default constructor.

Parameters:

connections - connections between points.

sampler - sampler for sampling along normals

numModelSamples - number of samples for the model

numSearchSamples - number of samples for search; must be bigger than numModelSamples

normalLength - length of the normal in intrinsic scale units

Method Detail

updateModel

public void updateModel(FImage image,
                        Point2d point,
                        PointList pointList)

Description copied from interface: LandmarkModel

Update the internal model of local image content by adding information from the provided image.

Specified by:

updateModel in interface LandmarkModel<FImage>

Parameters:

image - the image

point - the point in the image representing the landmark

pointList - the pointList to which the point belongs

computeCost

public float computeCost(FImage image,
                         Point2d point,
                         PointList pointList)

Description copied from interface: LandmarkModel

Evaluate the cost function using the given image and point. Lower costs indicate better fits.

Specified by:

computeCost in interface LandmarkModel<FImage>

Parameters:

image - the image

point - the point in the image

pointList - the pointList to which the point belongs

Returns:

the cost

updatePosition

public ObjectFloatPair<Point2d> updatePosition(FImage image,
                                               Point2d initial,
                                               PointList pointList)

Description copied from interface: LandmarkModel

Estimate an improved fit based on a local neighbourhood search. Returns the new best point and the distance moved normalised by the size of the search area. If the point didn't move, then the distance would be 0; if the point moved to the extremity of the search region, it would be 1.0.

Specified by:

updatePosition in interface LandmarkModel<FImage>

Parameters:

image - the image

initial - the initial point in the image

pointList - the pointList to which the point belongs

Returns:

the updated point