Feature normalization and likelihood-based similarity measures for image retrieval

被引：309

作者：

Aksoy, S ^{[1
]}

Haralick, RM ^{[1
]}

机构：

[1] Univ Washington, Dept Elect Engn, Intelligent Syst Lab, Seattle, WA 98195 USA

来源：

PATTERN RECOGNITION LETTERS | 2001年 / 22卷 / 05期

关键词：

feature normalization; Minkowsky metric; likelihood ratio; image retrieval; image similarity;

D O I：

10.1016/S0167-8655(00)00112-4

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Distance measures like the Euclidean distance are used to measure similarity between images in content-based image retrieval. Such geometric measures implicitly assign more weighting to features with large ranges than those with small ranges. This paper discusses the effects of five feature normalization methods on retrieval performance. We also describe two likelihood ratio-based similarity measures that perform significantly better than the commonly used geometric approaches like the L-p metrics. (C) 2001 Elsevier Science B.V. All rights reserved.

引用

页码：563 / 582

页数：20

共 26 条

[1]

Abramowitz M., 1972, HDB MATH FUNCTIONS F

[2] Textural features for image database retrieval [J].

Aksoy, S ;

Haralick, RM .

IEEE WORKSHOP ON CONTENT-BASED ACCESS OF IMAGE AND VIDEO LIBRARIES - PROCEEDINGS, 1998, :45-49

[3]

Aksoy S, 2000, PROC CVPR IEEE, P357, DOI 10.1109/CVPR.2000.854847

[4]

AKSOY S, 2000, TEXTURE ANAL MACHINE, V40

[5]

BELONGIE S, 1988, P IEEE INT C COMP VI

[6] Efficient image retrieval with multiple distance measures [J].

Berman, A ;

Shapiro, L .

STORAGE AND RETRIEVAL FOR IMAGE AND VIDEO DATABASES V, 1997, 3022 :12-21

[7]

BURY K.V., 1975, STAT MODELS APPL SCI

[8]

Casella G., 2021, STAT INFERENCE

[9]

CHEIKH FA, 1999, SPIE STORAGE RETRIEV, P98

[10]

FLICKNER M, 1993, SPIE STORAGE RETRIEV, P173

← 1 2 3 →