Organizing Similarity Spaces Using Metric Hulls

被引：1

作者：

Janosova, Miriama ^{[1
]}

Prochazka, David ^{[1
]}

Dohnal, Vlastislav ^{[1
]}

机构：

[1] Masaryk Univ, Fac Informat, Brno, Czech Republic

来源：

SIMILARITY SEARCH AND APPLICATIONS, SISAP 2021 | 2021年 / 13058卷

关键词：

Metric-hull tree; Metric hull; Index structure; Nearest-neighbor query; Similarity search;

D O I：

10.1007/978-3-030-89657-7_1

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A novel concept of a metric hull has recently been introduced to encompass a set of objects by a few selected border objects. Following one of the metric-hull computation methods that generate a hierarchy of metric hulls, we introduce a metric index structure for unstructured and complex data, a Metric Hull Tree (MH-tree). We propose a construction of MH-tree by a bulk-loading procedure and outline an insert operation. With respect to the design of the tree, we provide an implementation of an approximate kNN search operation. Finally, we utilized the Profimedia dataset to evaluate various building and ranking strategies of MH-tree and compared the results with M-tree.

引用

页码：3 / 16

页数：14

共 26 条

[1] MI-File: using inverted files for scalable approximate similarity search [J].