Approximate nearest neighbor searching in multimedia databases

H. Ferhatosmanoglu, E. Tuncel, D. Agrawal, A. El Abbadi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

83 Citations (Scopus)

Abstract

In is paper, we develop a general framework for approximate nearest neighbor queries. We categorize the current approaches for nearest neighbor query processing based on either their ability to reduce the data set that needs to be examined, or their ability to reduce the representation size of each data object. We first propose modifications to well-known techniques to support the progressive processing of approximate nearest neighbor queries. A user may therefore stop the retrieval process once enough information has been returned. We then develop a new technique based on clustering that merges the benefits of the two general classes of approaches. Our cluster-based approach allows a user to progressively explore the approximate results with increasing accuracy. We propose a new metric for evaluation of approximate nearest neighbor searching techniques. Using both the proposed and the traditional metrics, we analyze and compare several techniques with a detailed perforrnance evaluation. We demonstrate the feasibility and efficiency of approximate nearest neighbor searching. We perform experiments on several real data sets and establish the superiority of the proposed cluster-based technique over the existing techniques for approximate nearest neighbor searching.

Original languageEnglish
Title of host publicationProceedings - International Conference on Data Engineering
Pages503-511
Number of pages9
Publication statusPublished - 1 Jan 2001
Externally publishedYes
Event17th International Conference on Data Engineering - Heidelberg, Germany
Duration: 2 Apr 20016 Apr 2001

Other

Other17th International Conference on Data Engineering
CountryGermany
CityHeidelberg
Period2/4/016/4/01

Fingerprint

Query processing
Nearest neighbor search
Processing
Experiments

ASJC Scopus subject areas

  • Software
  • Engineering(all)
  • Engineering (miscellaneous)

Cite this

Ferhatosmanoglu, H., Tuncel, E., Agrawal, D., & El Abbadi, A. (2001). Approximate nearest neighbor searching in multimedia databases. In Proceedings - International Conference on Data Engineering (pp. 503-511)

Approximate nearest neighbor searching in multimedia databases. / Ferhatosmanoglu, H.; Tuncel, E.; Agrawal, D.; El Abbadi, A.

Proceedings - International Conference on Data Engineering. 2001. p. 503-511.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ferhatosmanoglu, H, Tuncel, E, Agrawal, D & El Abbadi, A 2001, Approximate nearest neighbor searching in multimedia databases. in Proceedings - International Conference on Data Engineering. pp. 503-511, 17th International Conference on Data Engineering, Heidelberg, Germany, 2/4/01.
Ferhatosmanoglu H, Tuncel E, Agrawal D, El Abbadi A. Approximate nearest neighbor searching in multimedia databases. In Proceedings - International Conference on Data Engineering. 2001. p. 503-511
Ferhatosmanoglu, H. ; Tuncel, E. ; Agrawal, D. ; El Abbadi, A. / Approximate nearest neighbor searching in multimedia databases. Proceedings - International Conference on Data Engineering. 2001. pp. 503-511
@inproceedings{634754c322f94e53bcf36c48782c60aa,
title = "Approximate nearest neighbor searching in multimedia databases",
abstract = "In is paper, we develop a general framework for approximate nearest neighbor queries. We categorize the current approaches for nearest neighbor query processing based on either their ability to reduce the data set that needs to be examined, or their ability to reduce the representation size of each data object. We first propose modifications to well-known techniques to support the progressive processing of approximate nearest neighbor queries. A user may therefore stop the retrieval process once enough information has been returned. We then develop a new technique based on clustering that merges the benefits of the two general classes of approaches. Our cluster-based approach allows a user to progressively explore the approximate results with increasing accuracy. We propose a new metric for evaluation of approximate nearest neighbor searching techniques. Using both the proposed and the traditional metrics, we analyze and compare several techniques with a detailed perforrnance evaluation. We demonstrate the feasibility and efficiency of approximate nearest neighbor searching. We perform experiments on several real data sets and establish the superiority of the proposed cluster-based technique over the existing techniques for approximate nearest neighbor searching.",
author = "H. Ferhatosmanoglu and E. Tuncel and D. Agrawal and {El Abbadi}, A.",
year = "2001",
month = "1",
day = "1",
language = "English",
pages = "503--511",
booktitle = "Proceedings - International Conference on Data Engineering",

}

TY - GEN

T1 - Approximate nearest neighbor searching in multimedia databases

AU - Ferhatosmanoglu, H.

AU - Tuncel, E.

AU - Agrawal, D.

AU - El Abbadi, A.

PY - 2001/1/1

Y1 - 2001/1/1

N2 - In is paper, we develop a general framework for approximate nearest neighbor queries. We categorize the current approaches for nearest neighbor query processing based on either their ability to reduce the data set that needs to be examined, or their ability to reduce the representation size of each data object. We first propose modifications to well-known techniques to support the progressive processing of approximate nearest neighbor queries. A user may therefore stop the retrieval process once enough information has been returned. We then develop a new technique based on clustering that merges the benefits of the two general classes of approaches. Our cluster-based approach allows a user to progressively explore the approximate results with increasing accuracy. We propose a new metric for evaluation of approximate nearest neighbor searching techniques. Using both the proposed and the traditional metrics, we analyze and compare several techniques with a detailed perforrnance evaluation. We demonstrate the feasibility and efficiency of approximate nearest neighbor searching. We perform experiments on several real data sets and establish the superiority of the proposed cluster-based technique over the existing techniques for approximate nearest neighbor searching.

AB - In is paper, we develop a general framework for approximate nearest neighbor queries. We categorize the current approaches for nearest neighbor query processing based on either their ability to reduce the data set that needs to be examined, or their ability to reduce the representation size of each data object. We first propose modifications to well-known techniques to support the progressive processing of approximate nearest neighbor queries. A user may therefore stop the retrieval process once enough information has been returned. We then develop a new technique based on clustering that merges the benefits of the two general classes of approaches. Our cluster-based approach allows a user to progressively explore the approximate results with increasing accuracy. We propose a new metric for evaluation of approximate nearest neighbor searching techniques. Using both the proposed and the traditional metrics, we analyze and compare several techniques with a detailed perforrnance evaluation. We demonstrate the feasibility and efficiency of approximate nearest neighbor searching. We perform experiments on several real data sets and establish the superiority of the proposed cluster-based technique over the existing techniques for approximate nearest neighbor searching.

UR - http://www.scopus.com/inward/record.url?scp=0034996152&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034996152&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0034996152

SP - 503

EP - 511

BT - Proceedings - International Conference on Data Engineering

ER -