Content-based image retrieval system with relevance feedback

Hanen Karamti, Mohamed Tmar, Faiez Gargouri

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

2 Citations (Scopus)

Abstract

In the Content-based image retrieval (CBIR) system, user can express his interest with an image to search images from large database. The retrieval technique uses only the visual contents of images. In recent years with the technological advances, there remain many challenging research problems that continue to attract researchers from multiple disciplines such as the indexing, storing and browsing in the large database. However, traditional methods of image retrieval might not be sufficiently effective when dealing these research problems. Therefore there is a need for an efficient way for facilitate to user to find his need in these large collections of images. Therefore, building a new system to retrieve images using the relevance feedback's technique is necessary in order to deal with such problem of image retrieval. In this paper, a new CBIR system is proposed to retrieve the similar images by integrating a relevance feedback. This system can be exploited to discover a new proper query representation and to improve the relevance of the retrieved results. The results obtained by our system are illustrated through some experiments on images from the MediaEval2014 collection.

Original languageEnglish
Title of host publicationWEBIST 2015 - 11th International Conference on Web Information Systems and Technologies, Proceedings
Pages287-292
Number of pages6
ISBN (Electronic)9789897581069
Publication statusPublished - 1 Jan 2015
Event11th International Conference on Web Information Systems and Technologies, WEBIST 2015 - Lisbon, Portugal
Duration: 20 May 201522 May 2015

Other

Other11th International Conference on Web Information Systems and Technologies, WEBIST 2015
CountryPortugal
CityLisbon
Period20/05/1522/05/15

Fingerprint

Image retrieval
Feedback
Experiments

Keywords

  • CBIR
  • Image
  • Neural network
  • Query
  • Relevance feedback
  • Rocchio

Cite this

Karamti, H., Tmar, M., & Gargouri, F. (2015). Content-based image retrieval system with relevance feedback. In WEBIST 2015 - 11th International Conference on Web Information Systems and Technologies, Proceedings (pp. 287-292)
Karamti, Hanen ; Tmar, Mohamed ; Gargouri, Faiez. / Content-based image retrieval system with relevance feedback. WEBIST 2015 - 11th International Conference on Web Information Systems and Technologies, Proceedings. 2015. pp. 287-292
@inproceedings{75acf40f1d7445158749e1c63764815d,
title = "Content-based image retrieval system with relevance feedback",
abstract = "In the Content-based image retrieval (CBIR) system, user can express his interest with an image to search images from large database. The retrieval technique uses only the visual contents of images. In recent years with the technological advances, there remain many challenging research problems that continue to attract researchers from multiple disciplines such as the indexing, storing and browsing in the large database. However, traditional methods of image retrieval might not be sufficiently effective when dealing these research problems. Therefore there is a need for an efficient way for facilitate to user to find his need in these large collections of images. Therefore, building a new system to retrieve images using the relevance feedback's technique is necessary in order to deal with such problem of image retrieval. In this paper, a new CBIR system is proposed to retrieve the similar images by integrating a relevance feedback. This system can be exploited to discover a new proper query representation and to improve the relevance of the retrieved results. The results obtained by our system are illustrated through some experiments on images from the MediaEval2014 collection.",
keywords = "CBIR, Image, Neural network, Query, Relevance feedback, Rocchio",
author = "Hanen Karamti and Mohamed Tmar and Faiez Gargouri",
year = "2015",
month = "1",
day = "1",
language = "English",
pages = "287--292",
booktitle = "WEBIST 2015 - 11th International Conference on Web Information Systems and Technologies, Proceedings",

}

Karamti, H, Tmar, M & Gargouri, F 2015, Content-based image retrieval system with relevance feedback. in WEBIST 2015 - 11th International Conference on Web Information Systems and Technologies, Proceedings. pp. 287-292, 11th International Conference on Web Information Systems and Technologies, WEBIST 2015, Lisbon, Portugal, 20/05/15.

Content-based image retrieval system with relevance feedback. / Karamti, Hanen; Tmar, Mohamed; Gargouri, Faiez.

WEBIST 2015 - 11th International Conference on Web Information Systems and Technologies, Proceedings. 2015. p. 287-292.

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

TY - GEN

T1 - Content-based image retrieval system with relevance feedback

AU - Karamti, Hanen

AU - Tmar, Mohamed

AU - Gargouri, Faiez

PY - 2015/1/1

Y1 - 2015/1/1

N2 - In the Content-based image retrieval (CBIR) system, user can express his interest with an image to search images from large database. The retrieval technique uses only the visual contents of images. In recent years with the technological advances, there remain many challenging research problems that continue to attract researchers from multiple disciplines such as the indexing, storing and browsing in the large database. However, traditional methods of image retrieval might not be sufficiently effective when dealing these research problems. Therefore there is a need for an efficient way for facilitate to user to find his need in these large collections of images. Therefore, building a new system to retrieve images using the relevance feedback's technique is necessary in order to deal with such problem of image retrieval. In this paper, a new CBIR system is proposed to retrieve the similar images by integrating a relevance feedback. This system can be exploited to discover a new proper query representation and to improve the relevance of the retrieved results. The results obtained by our system are illustrated through some experiments on images from the MediaEval2014 collection.

AB - In the Content-based image retrieval (CBIR) system, user can express his interest with an image to search images from large database. The retrieval technique uses only the visual contents of images. In recent years with the technological advances, there remain many challenging research problems that continue to attract researchers from multiple disciplines such as the indexing, storing and browsing in the large database. However, traditional methods of image retrieval might not be sufficiently effective when dealing these research problems. Therefore there is a need for an efficient way for facilitate to user to find his need in these large collections of images. Therefore, building a new system to retrieve images using the relevance feedback's technique is necessary in order to deal with such problem of image retrieval. In this paper, a new CBIR system is proposed to retrieve the similar images by integrating a relevance feedback. This system can be exploited to discover a new proper query representation and to improve the relevance of the retrieved results. The results obtained by our system are illustrated through some experiments on images from the MediaEval2014 collection.

KW - CBIR

KW - Image

KW - Neural network

KW - Query

KW - Relevance feedback

KW - Rocchio

UR - http://www.scopus.com/inward/record.url?scp=84945430982&partnerID=8YFLogxK

M3 - Conference contribution

SP - 287

EP - 292

BT - WEBIST 2015 - 11th International Conference on Web Information Systems and Technologies, Proceedings

ER -

Karamti H, Tmar M, Gargouri F. Content-based image retrieval system with relevance feedback. In WEBIST 2015 - 11th International Conference on Web Information Systems and Technologies, Proceedings. 2015. p. 287-292