org.openimaj.knn

Interface InternalNearestNeighbours<DISTANCES>

Type Parameters:

DISTANCES - The type of distances measured (usually an array type)

public interface InternalNearestNeighbours<DISTANCES>

Interface for K-nearest-neighbour implementations that are able to search directly using an indexed item of their own internal data as the query.

Author:

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

Method Summary

Methods

Modifier and Type	Method and Description
void	searchKNN(int[] qus, int K, int[][] nnIndices, DISTANCES[] nnDistances) Search for the K nearest neighbours to each of the N queries, and return the indices of each nearest neighbour and their respective distances.
void	searchNN(int[] qus, int[] nnIndices, DISTANCES nnDistances) Search for the nearest neighbour to each of the N queries (given by their index in this nearest neighbours object), and return the index of each nearest neighbour and the respective distance.

Method Detail

searchNN

void searchNN(int[] qus,
            int[] nnIndices,
            DISTANCES nnDistances)

Search for the nearest neighbour to each of the N queries (given by their index in this nearest neighbours object), and return the index of each nearest neighbour and the respective distance.

This method should not return the same index as the query (i.e. technically it should find the second-nearest-neighbour)

For efficiency, to use this method, you need to pre-construct the arrays for storing the results outside of the method and pass them in as arguments.

Parameters:

qus - An array of N query vectors

nnIndices - The return N-dimensional array for holding the indices of the nearest neighbour of each respective query.

nnDistances - The return N-dimensional array for holding the distances of the nearest neighbour to each respective query.

searchKNN

void searchKNN(int[] qus,
             int K,
             int[][] nnIndices,
             DISTANCES[] nnDistances)

Search for the K nearest neighbours to each of the N queries, and return the indices of each nearest neighbour and their respective distances.

This method should not return the same index as the query (i.e. technically it should find the second-nearest-neighbour as the first returned value)

For efficiency, to use this method, you need to pre-construct the arrays for storing the results outside of the method and pass them in as arguments.

Parameters:

qus - An array of N query indices

K - the number of neighbours to find

nnIndices - The return N*K-dimensional array for holding the indices of the K nearest neighbours of each respective query.

nnDistances - The return N*K-dimensional array for holding the distances of the nearest neighbours of each respective query.