Package boofcv.struct.kmeans

Class FactoryTupleCluster

java.lang.Object

boofcv.struct.kmeans.FactoryTupleCluster

public class FactoryTupleCluster
extends Object

Factory for creating classes related to clustering of TupleDesc data structures

Constructor Summary

Constructors

Constructor	Description
FactoryTupleCluster()

Method Summary

Modifier and Type	Method	Description
static <TD extends TupleDesc<TD>> PointDistance<TD>	createDistance(Class<TD> tuple)
static <TD extends TupleDesc<TD>> ComputeMeanClusters<TD>	createMeanClusters(int numElements, int minimumForThreads, Class<TD> type)
static <TD extends TupleDesc<TD>> StandardKMeans<TD>	kmeans(ConfigKMeans config, int minimumForThreads, int numElements, Class<TD> tupleType)	Creates a K-means clistering algorithm

Methods inherited from class java.lang.Object

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

Constructor Details

FactoryTupleCluster

public FactoryTupleCluster()

Method Details

kmeans

public static <TD extends TupleDesc<TD>>
StandardKMeans<TD> kmeans(ConfigKMeans config,
 int minimumForThreads,
 int numElements,
 Class<TD> tupleType)

Creates a K-means clistering algorithm

Parameters:

config - Configuration for K-Means clustering

minimumForThreads - Performance tuning parameter. A single threaded variant is used if the number of descriptors is less than this number.

numElements - Number of elements in the tuple

tupleType - Type of tuple

Returns:

Clustering algorithm

createMeanClusters

public static <TD extends TupleDesc<TD>>
ComputeMeanClusters<TD> createMeanClusters(int numElements,
 int minimumForThreads,
 Class<TD> type)

createDistance

public static <TD extends TupleDesc<TD>>
PointDistance<TD> createDistance(Class<TD> tuple)