org.openimaj.image.feature.local.aggregate

Class BagOfVisualWords<T>

java.lang.Object

org.openimaj.image.feature.local.aggregate.BagOfVisualWords<T>

Type Parameters:

T - Primitive array type of the ArrayFeatureVectors used by the LocalFeatures that will be processed.

All Implemented Interfaces:

VectorAggregator<ArrayFeatureVector<T>,SparseIntFV>

public class BagOfVisualWords<T>
extends Object
implements VectorAggregator<ArrayFeatureVector<T>,SparseIntFV>

Implementation of an object capable of extracting basic (hard-assignment) Bag of Visual Words (BoVW) representations of an image given a list of local features and an HardAssigner with an associated codebook.

Author:

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

Constructor Summary

Constructors

Constructor and Description
BagOfVisualWords(HardAssigner<T,?,?> assigner) Construct with the given assigner.

Method Summary

Modifier and Type	Method and Description
SparseIntFV	aggregate(List<? extends LocalFeature<?,? extends ArrayFeatureVector<T>>> features) Aggregate the given features into a vector.
SparseIntFV	aggregateVectors(List<? extends ArrayFeatureVector<T>> features) Aggregate the given features into a vector.
SparseIntFV	aggregateVectorsRaw(List<T> features) Aggregate the given features into a vector.
static <L extends Location,T> List<QuantisedLocalFeature<L>>	computeQuantisedFeatures(HardAssigner<T,?,?> assigner, List<? extends LocalFeature<L,? extends ArrayFeatureVector<T>>> features) Utility method to construct a list of quantised local features (local features with visual word assignments) from a list of features and a HardAssigner.
static <L extends Location> SparseIntFV	extractFeatureFromQuantised(Collection<? extends QuantisedLocalFeature<L>> qfeatures, int nfeatures) Utility method to quickly convert a collection of quantised local features to a histogram of their corresponding visual word identifiers.

Methods inherited from class java.lang.Object

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

Constructor Detail

BagOfVisualWords

public BagOfVisualWords(HardAssigner<T,?,?> assigner)

Construct with the given assigner.

Parameters:

assigner - the assigner

Method Detail

computeQuantisedFeatures

public static <L extends Location,T> List<QuantisedLocalFeature<L>> computeQuantisedFeatures(HardAssigner<T,?,?> assigner,
                                                                                             List<? extends LocalFeature<L,? extends ArrayFeatureVector<T>>> features)

Utility method to construct a list of quantised local features (local features with visual word assignments) from a list of features and a HardAssigner.

Parameters:

assigner - the assigner to apply to the feature vectors to create the visual word identifiers

features - the features to process

Returns:

a list of features with visual word assignments

extractFeatureFromQuantised

public static <L extends Location> SparseIntFV extractFeatureFromQuantised(Collection<? extends QuantisedLocalFeature<L>> qfeatures,
                                                                           int nfeatures)

Utility method to quickly convert a collection of quantised local features to a histogram of their corresponding visual word identifiers.

Parameters:

qfeatures - the quantised features.

nfeatures - the number of visual words.

Returns:

a histogram of the occurrences of the visual words

aggregate

public SparseIntFV aggregate(List<? extends LocalFeature<?,? extends ArrayFeatureVector<T>>> features)

Description copied from interface: VectorAggregator

Aggregate the given features into a vector.

Specified by:

aggregate in interface VectorAggregator<ArrayFeatureVector<T>,SparseIntFV>

Parameters:

features - the features to aggregate

Returns:

the aggregated vector

aggregateVectors

public SparseIntFV aggregateVectors(List<? extends ArrayFeatureVector<T>> features)

Description copied from interface: VectorAggregator

Aggregate the given features into a vector.

Specified by:

aggregateVectors in interface VectorAggregator<ArrayFeatureVector<T>,SparseIntFV>

Parameters:

features - the features to aggregate

Returns:

the aggregated vector

aggregateVectorsRaw

public SparseIntFV aggregateVectorsRaw(List<T> features)

Aggregate the given features into a vector.

Parameters:

features - the features to aggregate

Returns:

the aggregated vector