Node splitting algorithms in tree-structured high-dimensional indexes for similarity search

Authors:
Yongjian Fu;Jui-Che Teng;S. R. Subramanya
Affiliations:
University of Missouri-Rolla, Rolla, MO;University of Missouri-Rolla, Rolla, MO;University of Missouri-Rolla, Rolla, MO
Venue:
Proceedings of the 2002 ACM symposium on Applied computing
Year:
2002

Citing 6
Cited 1

Algorithms for clustering data

Algorithms for clustering data
The R*-tree: an efficient and robust access method for points and rectangles

SIGMOD '90 Proceedings of the 1990 ACM SIGMOD international conference on Management of data
The SR-tree: an index structure for high-dimensional nearest neighbor queries

SIGMOD '97 Proceedings of the 1997 ACM SIGMOD international conference on Management of data
R-trees: a dynamic index structure for spatial searching

SIGMOD '84 Proceedings of the 1984 ACM SIGMOD international conference on Management of data
Content-Based Image Retrieval Systems

Computer
Similarity Indexing with the SS-tree

ICDE '96 Proceedings of the Twelfth International Conference on Data Engineering

Corner-based splitting: An improved node splitting algorithm for R-tree

Journal of Information Science

Quantified Score

Hi-index	0.00

Visualization

Abstract

Content-based searches and retrievals in multimedia and image databases use high-dimensional indexing structures for organizing the features of the objects. Most of those index structures are tree-structured whose nodes have a limit on the number of entries describing the subtrees rooted at those nodes. When index trees are built by repeated insertion of entries, nodes need to be split and the tree balanced accordingly. Node-splitting algorithms eventually determine the final structure of the tree which will have a profound effect on the search performance. This paper presents a comparative study of several node splitting algorithms for a typical high-dimensional indexing structure. The algorithms are implemented and tested on an image database and the results are presented.