org.openimaj.ml.clustering

Interface SpatialClusterer<CLUSTERTYPE extends SpatialClusters<DATATYPE>,DATATYPE>

Type Parameters:

CLUSTERTYPE - The type of cluster produced.

DATATYPE - the primitive array datatype which represents a centroid of this cluster.

All Superinterfaces:

Clusterer<DATATYPE[]>

All Known Implementing Classes:

ByteKMeans, ClusterLimitedIntRAC, DoubleKDTreeClusterer, DoubleKMeans, DoubleNNDBSCAN, FeatureVectorKMeans, FloatKMeans, HierarchicalByteKMeans, HierarchicalDoubleKMeans, HierarchicalFloatKMeans, HierarchicalIntKMeans, HierarchicalLongKMeans, HierarchicalShortKMeans, IntKMeans, IntRAC, IntRandomForest, LongKMeans, RandomByteClusterer, RandomDoubleClusterer, RandomFloatClusterer, RandomIntClusterer, RandomLongClusterer, RandomSetByteClusterer, RandomSetDoubleClusterer, RandomSetFloatClusterer, RandomSetIntClusterer, RandomSetLongClusterer, RandomSetShortClusterer, RandomShortClusterer, ShortKMeans, SphericalKMeans

public interface SpatialClusterer<CLUSTERTYPE extends SpatialClusters<DATATYPE>,DATATYPE>
extends Clusterer<DATATYPE[]>

A SpatialClusterer clusters data that can be represented as points in a space. Each point is typically represented by a numerical coordinate vector.

Author:

Jonathon Hare (jsh2@ecs.soton.ac.uk), Sina Samangooei (ss@ecs.soton.ac.uk)

Method Summary

Modifier and Type	Method and Description
CLUSTERTYPE	cluster(DataSource<DATATYPE> data) Perform clustering with data from a data source.
CLUSTERTYPE	cluster(DATATYPE[] data) Perform clustering on the given data.

Methods inherited from interface org.openimaj.experiment.evaluation.cluster.processor.Clusterer

performClustering

Method Detail

cluster

CLUSTERTYPE cluster(DATATYPE[] data)

Perform clustering on the given data.

Parameters:

data - the data.

Returns:

the generated clusters.

cluster

CLUSTERTYPE cluster(DataSource<DATATYPE> data)

Perform clustering with data from a data source. The DataSource could potentially be backed by disk rather in memory.

Parameters:

data - the data.

Returns:

the generated clusters.