How to Cope with the Performance Gap in Content-Based Image Retrieval Systems

被引：2

作者：

Traina, Agma J. M. ^{[1
]}

Traina, Caetano, Jr. ^{[1
]}

Ciferri, Cristina D. A. ^{[1
]}

Ribeiro, Marcela X. ^{[3
]}

Azevedo-Marques, Paulo M. ^{[2
,4
]}

机构：

[1] Univ Sao Paulo, Comp Sci Dept, Sao Carlos, SP, Brazil

[2] Univ Sao Paulo, Sch Med, Internal Med Dept, Med Phys & Biomed Informat, Sao Carlos, SP, Brazil

[3] Univ Sao Paulo, Dept Comp Sci, Sao Carlos, SP, Brazil

[4] Univ Sao Paulo, Ribeirao Preto, Brazil

来源：

INTERNATIONAL JOURNAL OF HEALTHCARE INFORMATION SYSTEMS AND INFORMATICS | 2009年 / 4卷 / 01期

基金：

巴西圣保罗研究基金会;

关键词：

content-based image retrieval (CBIR); feature selection; image indexing; performance gap; semantic gap;

D O I：

10.4018/jhisi.2009010104

中图分类号：

R-058 [];

学科分类号：

摘要：

This paper discusses the main aspects regarding the performance gap in Content-based Image Retrieval (CBIR) systems, which is an important issue regarding their acceptability. We also detail the main problems that lead to the performance gap: the use of many features to represent images, the lack of appropriate indexing structures for images and features, deficient query plans employed to execute similarity queries, and sometimes the poor quality of results obtained by the CBIR system. We present guidelines to overcome these problems by employing feature selection techniques to beat the "dimensionality curse", by using proper access methods to support fast and effective indexing and retrieval of images, by stressing the importance of using query optimization approaches and by including the user during the tuning of the CBIR system through relevance feedback techniques.

引用

页码：47 / 67

页数：21

共 50 条

[31] An overview of approaches for content-based medical image retrieval
Das P.
Neelima A.
International Journal of Multimedia Information Retrieval, 2017, 6 (4) : 271 - 280
[32] Content-based Image Retrieval for Scientific Literature Access
Deserno, T. M.
Antani, S.
Long, L. Rodney
METHODS OF INFORMATION IN MEDICINE, 2009, 48 (04) : 371 - 380
[33] Content-based image retrieval at the end of the early years
Smeulders, AWM
Worring, M
Santini, S
Gupta, A
Jain, R
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2000, 22 (12) : 1349 - 1380
[34] The fuzzy similarity measures for content-based image retrieval
Li, Y
Liu, JM
Li, J
Deng, W
Ye, CX
Wu, ZF
2003 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-5, PROCEEDINGS, 2003, : 3224 - 3228
[35] Application of fuzzy logic in content-based image retrieval
王小玲
谢康林
Journal of Harbin Institute of Technology(New series), 2008, (03) : 386 - 392
[36] Dynamic Exploratory Search in Content-Based Image Retrieval
Pyykko, Joel
Glowacka, Dorota
IMAGE ANALYSIS, SCIA 2017, PT I, 2017, 10269 : 538 - 549
[37] ReliefF Based Feature Selection In Content-Based Image Retrieval
Sarrafzadeh, Abdolhossein
Atabay, Habibollah Agh
Pedram, Mir Mosen
Shanbehzadeh, Jamshid
INTERNATIONAL MULTICONFERENCE OF ENGINEERS AND COMPUTER SCIENTISTS, IMECS 2012, VOL I, 2012, : 19 - 22
[38] Indexing of Content-Based Image Retrieval System with Image Understanding Approach
Li Xuelong
Journal of Systems Engineering and Electronics, 2003, (02) : 63 - 68
[39] A simultaneous feature adaptation and feature selection method for content-based image retrieval systems
Rashedi, Esmat
Nezamabadi-pour, Hossein
Saryazdi, Saeid
KNOWLEDGE-BASED SYSTEMS, 2013, 39 : 85 - 94
[40] Image background search: Combining object detection techniques with content-based image retrieval (CBIR) systems
Srihari, R
Zhang, ZF
Rao, AB
IEEE WORKSHOP ON CONTENT-BASED ACCESS OF IMAGE AND VIDEO LIBRARIES (CBAIVL'99) - PROCEEDINGS, 1999, : 97 - 101

← 1 2 3 4 5 →