Package org.ddogleg.nn

Class FactoryNearestNeighbor

java.lang.Object

org.ddogleg.nn.FactoryNearestNeighbor

public class FactoryNearestNeighbor
extends Object

Factory for creating implementations of NearestNeighbor.

Constructor Summary

Constructors

Constructor	Description
FactoryNearestNeighbor()

Method Summary

Modifier and Type	Method	Description
static <P> NearestNeighbor<P>	exhaustive(KdTreeDistance<P> distance)	Performs an optimal NearestNeighbor by exhaustively consider all possible solutions.
static <P> NearestNeighbor<P>	generic(ConfigNearestNeighborSearch config, KdTreeDistance<P> distance)	Factory for generic NearestNeighbor.
static <P> NearestNeighbor<P>	kdRandomForest(KdTreeDistance<P> distance, int maxNodesSearched, int numTrees, int numConsiderSplit, long randomSeed)	Approximate NearestNeighbor search which uses a set of randomly generated K-D trees and a Best-Bin-First search.
static <P> NearestNeighbor<P>	kdtree(KdTreeDistance<P> distance)	Performs an optimal NearestNeighbor search using K-D tree.
static <P> NearestNeighbor<P>	kdtree(KdTreeDistance<P> distance, int maxNodesSearched)	Performs an approximate NearestNeighbor search using K-D tree.
static NearestNeighbor<double[]>	vptree(long randSeed)	Vantage point tree implementation for nearest neighbor search.

Methods inherited from class java.lang.Object

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

Constructor Details

FactoryNearestNeighbor

public FactoryNearestNeighbor()

Method Details

generic

public static <P> NearestNeighbor<P> generic(ConfigNearestNeighborSearch config,
 KdTreeDistance<P> distance)

Factory for generic NearestNeighbor.

kdtree

public static <P> NearestNeighbor<P> kdtree(KdTreeDistance<P> distance)

Performs an optimal NearestNeighbor search using K-D tree. Distance measure is Euclidean squared.

Type Parameters:

P - Point type.

Parameters:

distance - Specifies how distance is computed between two points.

Returns:

NearestNeighbor implementation

See Also:

• KdTreeNearestNeighbor
• AxisSplitterMedian

kdtree

public static <P> NearestNeighbor<P> kdtree(KdTreeDistance<P> distance,
 int maxNodesSearched)

Performs an approximate NearestNeighbor search using K-D tree. Node are searched in Best-Bin-First order. Distance measure is Euclidean squared.

Type Parameters:

P - Point type.

Parameters:

maxNodesSearched - Maximum number of nodes it will search. Controls speed and accuracy.

distance - Specifies how distance is computed between two points.

Returns:

NearestNeighbor implementation

See Also:

• KdTreeNearestNeighbor
• KdTreeSearch1Bbf
• AxisSplitterMedian

kdRandomForest

public static <P> NearestNeighbor<P> kdRandomForest(KdTreeDistance<P> distance,
 int maxNodesSearched,
 int numTrees,
 int numConsiderSplit,
 long randomSeed)

Approximate NearestNeighbor search which uses a set of randomly generated K-D trees and a Best-Bin-First search. Designed to work in high dimensional space. Distance measure is Euclidean squared.

Type Parameters:

P - Point type.

Parameters:

distance - Specifies how distance is computed between two points.

maxNodesSearched - Maximum number of nodes it will search. Controls speed and accuracy.

numTrees - Number of trees that are considered. Try 10 and tune.

numConsiderSplit - Number of nodes that are considered when generating a tree. Must be less than the point's dimension. Try 5

randomSeed - Seed used by random number generator

Returns:

NearestNeighbor implementation

See Also:

• KdForestBbfNearestNeighbor
• AxisSplitterMedian

exhaustive

public static <P> NearestNeighbor<P> exhaustive(KdTreeDistance<P> distance)

Performs an optimal NearestNeighbor by exhaustively consider all possible solutions. Distance measure is Euclidean squared.

Parameters:

distance - Specifies how distance is computed between two points.

Returns:

NearestNeighbor implementation

See Also:

• ExhaustiveNeighbor

vptree

public static NearestNeighbor<double[]> vptree(long randSeed)

Vantage point tree implementation for nearest neighbor search. Slower than KD-Tree on random data, but faster than it for some pathological cases.

Parameters:

randSeed - Random seed

Returns:

NearestNeighbor implementation

See Also:

• VpTree