A novel region-based image retrieval method using relevance feedback

F. Jing; B. Zhang; F. Lin; W. Y. Ma; H. J. Zhang

doi:10.1145/500933.500943

A novel region-based image retrieval method using relevance feedback

F. Jing, B. Zhang, F. Lin, W. Y. Ma, H. J. Zhang

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

27 Citations (Scopus)

Abstract

Content-based image retrieval using region segmentation has been an active research area in the past few years. Contrasting to traditional approaches, which compute only global features of images, the region-based methods extract features of the segmented regions and perform similarity comparisons at the granularity of region. In this paper, we propose a novel region-based retrieval method, Self-Learned Region Importance (SLRI). In this method, image similarity measure is based on the region importance learned from user's feedback. The region importance that coincides with human perception can not only be used in a query session, but also be memorized and cumulated for future queries. Experimental results on a database of about 8,600 general-purpose images show the effectiveness of our method.

Original language	English
Title of host publication	Proceedings of the ACM International Multimedia Conference and Exhibition
Publisher	Association for Computing Machinery
Pages	28-31
DOIs	https://doi.org/10.1145/500933.500943
Publication status	Published - 2001
Externally published	Yes
Event	-ACM Multimedia 2001 Workshops-Multimedia Information Retrieval - Ottawa, Ont., Canada Duration: 5 Oct 2001 → 5 Oct 2001

Conference

Conference	-ACM Multimedia 2001 Workshops-Multimedia Information Retrieval
Place	Canada
City	Ottawa, Ont.
Period	5/10/01 → 5/10/01

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Research Keywords

Feedback
Region importance
Region-based image retrieval

Access Output

10.1145/500933.500943

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{645a6697986f407f93002edc5d98a147,

title = "A novel region-based image retrieval method using relevance feedback",

abstract = "Content-based image retrieval using region segmentation has been an active research area in the past few years. Contrasting to traditional approaches, which compute only global features of images, the region-based methods extract features of the segmented regions and perform similarity comparisons at the granularity of region. In this paper, we propose a novel region-based retrieval method, Self-Learned Region Importance (SLRI). In this method, image similarity measure is based on the region importance learned from user's feedback. The region importance that coincides with human perception can not only be used in a query session, but also be memorized and cumulated for future queries. Experimental results on a database of about 8,600 general-purpose images show the effectiveness of our method.",

keywords = "Feedback, Region importance, Region-based image retrieval",

author = "F. Jing and B. Zhang and F. Lin and Ma, {W. Y.} and Zhang, {H. J.}",

note = "Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].; -ACM Multimedia 2001 Workshops-Multimedia Information Retrieval ; Conference date: 05-10-2001 Through 05-10-2001",

year = "2001",

doi = "10.1145/500933.500943",

language = "English",

pages = "28--31",

booktitle = "Proceedings of the ACM International Multimedia Conference and Exhibition",

publisher = "Association for Computing Machinery",

address = "United States",

}

Jing, F, Zhang, B, Lin, F, Ma, WY & Zhang, HJ 2001, A novel region-based image retrieval method using relevance feedback. in Proceedings of the ACM International Multimedia Conference and Exhibition. Association for Computing Machinery, pp. 28-31, -ACM Multimedia 2001 Workshops-Multimedia Information Retrieval, Ottawa, Ont., Canada, 5/10/01. https://doi.org/10.1145/500933.500943

A novel region-based image retrieval method using relevance feedback. / Jing, F.; Zhang, B.; Lin, F. et al.
Proceedings of the ACM International Multimedia Conference and Exhibition. Association for Computing Machinery, 2001. p. 28-31.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - A novel region-based image retrieval method using relevance feedback

AU - Jing, F.

AU - Zhang, B.

AU - Lin, F.

AU - Ma, W. Y.

AU - Zhang, H. J.

N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

PY - 2001

Y1 - 2001

N2 - Content-based image retrieval using region segmentation has been an active research area in the past few years. Contrasting to traditional approaches, which compute only global features of images, the region-based methods extract features of the segmented regions and perform similarity comparisons at the granularity of region. In this paper, we propose a novel region-based retrieval method, Self-Learned Region Importance (SLRI). In this method, image similarity measure is based on the region importance learned from user's feedback. The region importance that coincides with human perception can not only be used in a query session, but also be memorized and cumulated for future queries. Experimental results on a database of about 8,600 general-purpose images show the effectiveness of our method.

AB - Content-based image retrieval using region segmentation has been an active research area in the past few years. Contrasting to traditional approaches, which compute only global features of images, the region-based methods extract features of the segmented regions and perform similarity comparisons at the granularity of region. In this paper, we propose a novel region-based retrieval method, Self-Learned Region Importance (SLRI). In this method, image similarity measure is based on the region importance learned from user's feedback. The region importance that coincides with human perception can not only be used in a query session, but also be memorized and cumulated for future queries. Experimental results on a database of about 8,600 general-purpose images show the effectiveness of our method.

KW - Feedback

KW - Region importance

KW - Region-based image retrieval

UR - http://www.scopus.com/inward/record.url?scp=0034787244&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0034787244&origin=recordpage

U2 - 10.1145/500933.500943

DO - 10.1145/500933.500943

M3 - RGC 32 - Refereed conference paper (with host publication)

SP - 28

EP - 31

BT - Proceedings of the ACM International Multimedia Conference and Exhibition

PB - Association for Computing Machinery

T2 - -ACM Multimedia 2001 Workshops-Multimedia Information Retrieval

Y2 - 5 October 2001 through 5 October 2001

ER -

A novel region-based image retrieval method using relevance feedback

Abstract

Conference

Bibliographical note

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this