Data structures and algorithms for nearest neighbor search in general metric spaces
Peter N. Yianilos
- pp 311-321
Reads0
Chats0
TLDR
The up-tree (vantage point tree) is introduced in several forms, together‘ with &&ciated algorithms, as an improved method for these difficult search problems in general metric spaces.Abstract:
We consider the computational problem of finding nearest neighbors in general metric spaces. Of particular interest are spaces that may not be conveniently embedded or approximated in Euclidian space, or where the dimensionality of a Euclidian representation 1s very high. Also relevant are high-dimensional Euclidian settings in which the distribution of data is in some sense of lower dimension and embedded in the space. The up-tree (vantage point tree) is introduced in several forms, together‘ with &&ciated algorithms, as an improved method for these difficult search nroblems. Tree construcI tion executes in O(nlog(n i ) time, and search is under certain circumstances and in the imit, O(log(n)) expected time. The theoretical basis for this approach is developed and the results of several experiments are reported. In Euclidian cases, kd-tree performance is compared.read more
Citations
More filters
Posted Content
Generalized Shape Metrics on Neural Representations
TL;DR: In this article, the authors define a broad family of metric spaces that quantify representational dissimilarity between biological and artificial networks, and modify existing representational similarity measures based on canonical correlation analysis to satisfy the triangle inequality.
Book ChapterDOI
An indexing approach for representing multimedia objects in high-dimensional spaces based on expectation maximization algorithm
TL;DR: A new indexing approach to representing multimedia object classes generated by the Expectation Maximization clustering algorithm in a balanced and dynamic tree structure that provides a simple and practical solution to index clustered data and support efficient retrieval of the nearest neighbors in high dimensional object spaces.
Patent
Methods for using extracted features to perform an action
Abstract: A computer system comprising one or more processors and computer-readable media operatively connected thereto, having stored thereon instructions for carrying out the steps of: maintaining one or more databases comprising first electronic data comprising digitally created reference compact electronic representations for each of a plurality of reference electronic works and second electronic data associated with the reference electronic works and related to action information corresponding thereto; obtaining a first digitally created compact electronic representation comprising one or more extracted feature vectors of a first electronic work; identifying a matching reference electronic work by comparing the first digitally created compact electronic representation of the first electronic work with the first electronic data using a sub-linear search of the first electronic data; determining the action information corresponding to the matching reference electronic work based on the second electronic data; and associating the determined action information with the first electronic work.
Journal ArticleDOI
Pushing diversity into higher dimensions: The LID effect on diversified similarity searching
Daniel L. Jasbick,Lucio F. D. Santos,Paulo Mazzoncini de Azevedo-Marques,Agma J. M. Traina,Daniel de Oliveira,Marcos V. N. Bedo +5 more
TL;DR: In this paper , the authors apply the concept of Local Intrinsic Dimensionality (LID) to examine the behavior of the method diversity browsing in the exploration of high-dimensional data.
Comparação entre Diferentes Implementações de BK-trees para o Problema de Busca por Intervalo
Andre Luciano Rakowski,Natan Luiz Paetzhold Berwaldt,Mauricio Vielmo Schmaedeck,Sergio Luis Sardi Mergen +3 more
TL;DR: This paper analyzes different ways of implementing BK-trees, a pivot based indexing mechanism that achieves good results for similarity search for range queries, and investigates variations in terms of space cost, indexing time and search time.
References
More filters
Book
Introduction to Statistical Pattern Recognition
TL;DR: This completely revised second edition presents an introduction to statistical pattern recognition, which is appropriate as a text for introductory courses in pattern recognition and as a reference book for workers in the field.
Journal ArticleDOI
Voronoi diagrams—a survey of a fundamental geometric data structure
TL;DR: The Voronoi diagram as discussed by the authors divides the plane according to the nearest-neighbor points in the plane, and then divides the vertices of the plane into vertices, where vertices correspond to vertices in a plane.
Journal ArticleDOI
An Algorithm for Finding Best Matches in Logarithmic Expected Time
TL;DR: An algorithm and data structure are presented for searching a file containing N records, each described by k real valued keys, for the m closest matches or nearest neighbors to a given query record.
Journal ArticleDOI
A Branch and Bound Algorithm for Computing k-Nearest Neighbors
TL;DR: The method of branch and bound is implemented in the present algorithm to facilitate rapid calculation of the k-nearest neighbors, by eliminating the necesssity of calculating many distances.