org.openimaj.feature.local.matcher

Class BasicMatcher<T extends LocalFeature<?,?>>

java.lang.Object

org.openimaj.feature.local.matcher.BasicMatcher<T>

Type Parameters:

T -

All Implemented Interfaces:

LocalFeatureMatcher<T>

Direct Known Subclasses:

FastBasicKeypointMatcher

@Reference(type=Article,author="David Lowe",title="Distinctive image features from scale-invariant keypoints",year="2004",journal="IJCV",pages={"91","110"},month="January",number="2",volume="60") @Reference(type=Inproceedings,author="David Lowe",title="Object recognition from local scale-invariant features",year="1999",booktitle="Proc. of the International Conference on Computer Vision {ICCV}",pages={"1150","1157"})
public class BasicMatcher<T extends LocalFeature<?,?>>
extends Object
implements LocalFeatureMatcher<T>

Basic local feature matcher. Matches interest points by finding closest two interest points to target and checking whether the distance between the two matches is sufficiently large.

Author:

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

Field Summary

Fields

Modifier and Type	Field and Description
protected List<Pair<T>>	matches
protected List<T>	modelKeypoints
protected int	thresh

Constructor Summary

Constructors

Constructor and Description
BasicMatcher(int threshold) Initialise the matcher setting the threshold which the difference between the scores of the top two best matches must differ in order to count the first as a good match.

Method Summary

Modifier and Type	Method and Description
protected T	checkForMatch(T query, List<T> features) This searches through the keypoints in klist for the two closest matches to key.
boolean	findMatches(List<T> keys1) Attempt to find matches between the model features from the database, and given query features.
List<Pair<T>>	getMatches() Get the matches detected by the underlying algorithm
void	setModelFeatures(List<T> modelkeys) Set the features that represent the database to match queries against
void	setThreshold(int thresh) Set the matching threshold

Methods inherited from class java.lang.Object

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

Field Detail

modelKeypoints

protected List<T extends LocalFeature<?,?>> modelKeypoints

matches

protected List<Pair<T extends LocalFeature<?,?>>> matches

thresh

protected int thresh

Constructor Detail

BasicMatcher

public BasicMatcher(int threshold)

Initialise the matcher setting the threshold which the difference between the scores of the top two best matches must differ in order to count the first as a good match.

Parameters:

threshold - (as an integer percentage)

Method Detail

getMatches

public List<Pair<T>> getMatches()

Description copied from interface: LocalFeatureMatcher

Get the matches detected by the underlying algorithm

Specified by:

getMatches in interface LocalFeatureMatcher<T extends LocalFeature<?,?>>

Returns:

List of pairs of matching keypoints

findMatches

public boolean findMatches(List<T> keys1)

Description copied from interface: LocalFeatureMatcher

Attempt to find matches between the model features from the database, and given query features.

Specified by:

findMatches in interface LocalFeatureMatcher<T extends LocalFeature<?,?>>

Parameters:

keys1 - features from the query

Returns:

whether matches were found

checkForMatch

protected T checkForMatch(T query,
                          List<T> features)

This searches through the keypoints in klist for the two closest matches to key. If the closest is less than threshold times distance to second closest, then return the closest match. Otherwise, return NULL.

setModelFeatures

public void setModelFeatures(List<T> modelkeys)

Description copied from interface: LocalFeatureMatcher

Set the features that represent the database to match queries against

Specified by:

setModelFeatures in interface LocalFeatureMatcher<T extends LocalFeature<?,?>>

Parameters:

modelkeys - database of features

setThreshold

public void setThreshold(int thresh)

Set the matching threshold

Parameters:

thresh - the threshold