org.openimaj.image.feature.local.aggregate

Class SoftBagOfVisualWords<DATATYPE,DISTANCE>

java.lang.Object

org.openimaj.image.feature.local.aggregate.SoftBagOfVisualWords<DATATYPE,DISTANCE>

Type Parameters:

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

DISTANCE - Primitive array datatype for recording distances between points and cluster centroids

All Implemented Interfaces:

VectorAggregator<ArrayFeatureVector<DATATYPE>,SparseDoubleFV>

public class SoftBagOfVisualWords<DATATYPE,DISTANCE>
extends Object
implements VectorAggregator<ArrayFeatureVector<DATATYPE>,SparseDoubleFV>

Implementation of an object capable of extracting the soft-assigned Bag of Visual Words (BoVW) representation of an image given a list of local features and an SoftAssigner with an associated codebook. Soft-assignment assigns a single feature to multiple visual words, usually with some weighting for each word.

Author:

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

Constructor Summary

Constructors

Constructor and Description
SoftBagOfVisualWords(SoftAssigner<DATATYPE,DISTANCE> assigner) Construct with the given assigner.

Method Summary

Methods

Modifier and Type	Method and Description
SparseDoubleFV	aggregate(List<? extends LocalFeature<?,? extends ArrayFeatureVector<DATATYPE>>> features) Aggregate the given features into a vector.

Methods inherited from class java.lang.Object

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

Constructor Detail

SoftBagOfVisualWords

public SoftBagOfVisualWords(SoftAssigner<DATATYPE,DISTANCE> assigner)

Construct with the given assigner.

Parameters:

assigner - the assigner

Method Detail

aggregate

public SparseDoubleFV aggregate(List<? extends LocalFeature<?,? extends ArrayFeatureVector<DATATYPE>>> features)

Description copied from interface: VectorAggregator

Aggregate the given features into a vector.

Specified by:

aggregate in interface VectorAggregator<ArrayFeatureVector<DATATYPE>,SparseDoubleFV>

Parameters:

features - the features to aggregate

Returns:

the aggregated vector