SOM-based R∗-tree for similarity retrieval

Kun Seok Oh, Yaokai Feng, K. Kaneko, A. Makinouchi, Sang Hyun Bae

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

5 Citations (Scopus)

Abstract

Feature-based similarity retrieval has become an important research issue in multimedia database systems. The features of multimedia data are useful for discriminating between multimedia objects (e.g., documents, images, video, music score, etc.). For example, images are represented by their color histograms, texture vectors, and shape descriptors. A feature vector is a vector that represents a set of features, and are usually high-dimensional data. The performance of conventional multidimensional data structures (e.g., R-tree family K-D-B tree, grid file, TV-tree) tends to deteriorate as the number of dimensions of feature vectors increases. The R∗-tree is the most successful variant of the R-tree. We propose a SOM-based R∗-tree as a new indexing method for high-dimensional feature vectors. The SOM-based R∗-tree combines SOM and R∗-tree to achieve search performance more scalable to high dimensionalities. Self-organizing maps (SOMs) provide mapping from high-dimensional feature vectors onto a two-dimensional space. The mapping preserves the topology of the feature vectors. The map is called a topological feature map, and preserves the mutual relationships (similarity) in the feature spaces of input data, clustering mutually similar feature vectors in neighboring nodes. We experimentally compare the retrieval time cost of a SOM-based R∗-tree with that of an SOM and an R∗-tree using color feature vectors extracted from 40,000 images.

Original languageEnglish
Title of host publicationProceedings - 7th International Conference on Database Systems for Advanced Applications, DASFAA 2001
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages182-189
Number of pages8
ISBN (Electronic)0769509967, 9780769509969
DOIs
Publication statusPublished - Jan 1 2001
Event7th International Conference on Database Systems for Advanced Applications, DASFAA 2001 - Hong Kong, China
Duration: Apr 18 2001Apr 21 2001

Publication series

NameProceedings - 7th International Conference on Database Systems for Advanced Applications, DASFAA 2001

Other

Other7th International Conference on Database Systems for Advanced Applications, DASFAA 2001
CountryChina
CityHong Kong
Period4/18/014/21/01

Fingerprint

Self organizing maps
Color
Data structures
Textures
Topology

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems

Cite this

Oh, K. S., Feng, Y., Kaneko, K., Makinouchi, A., & Bae, S. H. (2001). SOM-based R∗-tree for similarity retrieval. In Proceedings - 7th International Conference on Database Systems for Advanced Applications, DASFAA 2001 (pp. 182-189). [916377] (Proceedings - 7th International Conference on Database Systems for Advanced Applications, DASFAA 2001). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DASFAA.2001.916377

SOM-based R∗-tree for similarity retrieval. / Oh, Kun Seok; Feng, Yaokai; Kaneko, K.; Makinouchi, A.; Bae, Sang Hyun.

Proceedings - 7th International Conference on Database Systems for Advanced Applications, DASFAA 2001. Institute of Electrical and Electronics Engineers Inc., 2001. p. 182-189 916377 (Proceedings - 7th International Conference on Database Systems for Advanced Applications, DASFAA 2001).

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

Oh, KS, Feng, Y, Kaneko, K, Makinouchi, A & Bae, SH 2001, SOM-based R∗-tree for similarity retrieval. in Proceedings - 7th International Conference on Database Systems for Advanced Applications, DASFAA 2001., 916377, Proceedings - 7th International Conference on Database Systems for Advanced Applications, DASFAA 2001, Institute of Electrical and Electronics Engineers Inc., pp. 182-189, 7th International Conference on Database Systems for Advanced Applications, DASFAA 2001, Hong Kong, China, 4/18/01. https://doi.org/10.1109/DASFAA.2001.916377
Oh KS, Feng Y, Kaneko K, Makinouchi A, Bae SH. SOM-based R∗-tree for similarity retrieval. In Proceedings - 7th International Conference on Database Systems for Advanced Applications, DASFAA 2001. Institute of Electrical and Electronics Engineers Inc. 2001. p. 182-189. 916377. (Proceedings - 7th International Conference on Database Systems for Advanced Applications, DASFAA 2001). https://doi.org/10.1109/DASFAA.2001.916377
Oh, Kun Seok ; Feng, Yaokai ; Kaneko, K. ; Makinouchi, A. ; Bae, Sang Hyun. / SOM-based R∗-tree for similarity retrieval. Proceedings - 7th International Conference on Database Systems for Advanced Applications, DASFAA 2001. Institute of Electrical and Electronics Engineers Inc., 2001. pp. 182-189 (Proceedings - 7th International Conference on Database Systems for Advanced Applications, DASFAA 2001).
@inproceedings{3a21bc049188479ea651c926b080702a,
title = "SOM-based R∗-tree for similarity retrieval",
abstract = "Feature-based similarity retrieval has become an important research issue in multimedia database systems. The features of multimedia data are useful for discriminating between multimedia objects (e.g., documents, images, video, music score, etc.). For example, images are represented by their color histograms, texture vectors, and shape descriptors. A feature vector is a vector that represents a set of features, and are usually high-dimensional data. The performance of conventional multidimensional data structures (e.g., R-tree family K-D-B tree, grid file, TV-tree) tends to deteriorate as the number of dimensions of feature vectors increases. The R∗-tree is the most successful variant of the R-tree. We propose a SOM-based R∗-tree as a new indexing method for high-dimensional feature vectors. The SOM-based R∗-tree combines SOM and R∗-tree to achieve search performance more scalable to high dimensionalities. Self-organizing maps (SOMs) provide mapping from high-dimensional feature vectors onto a two-dimensional space. The mapping preserves the topology of the feature vectors. The map is called a topological feature map, and preserves the mutual relationships (similarity) in the feature spaces of input data, clustering mutually similar feature vectors in neighboring nodes. We experimentally compare the retrieval time cost of a SOM-based R∗-tree with that of an SOM and an R∗-tree using color feature vectors extracted from 40,000 images.",
author = "Oh, {Kun Seok} and Yaokai Feng and K. Kaneko and A. Makinouchi and Bae, {Sang Hyun}",
year = "2001",
month = "1",
day = "1",
doi = "10.1109/DASFAA.2001.916377",
language = "English",
series = "Proceedings - 7th International Conference on Database Systems for Advanced Applications, DASFAA 2001",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "182--189",
booktitle = "Proceedings - 7th International Conference on Database Systems for Advanced Applications, DASFAA 2001",
address = "United States",

}

TY - GEN

T1 - SOM-based R∗-tree for similarity retrieval

AU - Oh, Kun Seok

AU - Feng, Yaokai

AU - Kaneko, K.

AU - Makinouchi, A.

AU - Bae, Sang Hyun

PY - 2001/1/1

Y1 - 2001/1/1

N2 - Feature-based similarity retrieval has become an important research issue in multimedia database systems. The features of multimedia data are useful for discriminating between multimedia objects (e.g., documents, images, video, music score, etc.). For example, images are represented by their color histograms, texture vectors, and shape descriptors. A feature vector is a vector that represents a set of features, and are usually high-dimensional data. The performance of conventional multidimensional data structures (e.g., R-tree family K-D-B tree, grid file, TV-tree) tends to deteriorate as the number of dimensions of feature vectors increases. The R∗-tree is the most successful variant of the R-tree. We propose a SOM-based R∗-tree as a new indexing method for high-dimensional feature vectors. The SOM-based R∗-tree combines SOM and R∗-tree to achieve search performance more scalable to high dimensionalities. Self-organizing maps (SOMs) provide mapping from high-dimensional feature vectors onto a two-dimensional space. The mapping preserves the topology of the feature vectors. The map is called a topological feature map, and preserves the mutual relationships (similarity) in the feature spaces of input data, clustering mutually similar feature vectors in neighboring nodes. We experimentally compare the retrieval time cost of a SOM-based R∗-tree with that of an SOM and an R∗-tree using color feature vectors extracted from 40,000 images.

AB - Feature-based similarity retrieval has become an important research issue in multimedia database systems. The features of multimedia data are useful for discriminating between multimedia objects (e.g., documents, images, video, music score, etc.). For example, images are represented by their color histograms, texture vectors, and shape descriptors. A feature vector is a vector that represents a set of features, and are usually high-dimensional data. The performance of conventional multidimensional data structures (e.g., R-tree family K-D-B tree, grid file, TV-tree) tends to deteriorate as the number of dimensions of feature vectors increases. The R∗-tree is the most successful variant of the R-tree. We propose a SOM-based R∗-tree as a new indexing method for high-dimensional feature vectors. The SOM-based R∗-tree combines SOM and R∗-tree to achieve search performance more scalable to high dimensionalities. Self-organizing maps (SOMs) provide mapping from high-dimensional feature vectors onto a two-dimensional space. The mapping preserves the topology of the feature vectors. The map is called a topological feature map, and preserves the mutual relationships (similarity) in the feature spaces of input data, clustering mutually similar feature vectors in neighboring nodes. We experimentally compare the retrieval time cost of a SOM-based R∗-tree with that of an SOM and an R∗-tree using color feature vectors extracted from 40,000 images.

UR - http://www.scopus.com/inward/record.url?scp=84963860755&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84963860755&partnerID=8YFLogxK

U2 - 10.1109/DASFAA.2001.916377

DO - 10.1109/DASFAA.2001.916377

M3 - Conference contribution

AN - SCOPUS:84963860755

T3 - Proceedings - 7th International Conference on Database Systems for Advanced Applications, DASFAA 2001

SP - 182

EP - 189

BT - Proceedings - 7th International Conference on Database Systems for Advanced Applications, DASFAA 2001

PB - Institute of Electrical and Electronics Engineers Inc.

ER -