Automatic adaptive metadata generation for image retrieval

Hideyasu Sasaki; Yasushi Kiyoki

Automatic adaptive metadata generation for image retrieval

Hideyasu Sasaki, Yasushi Kiyoki

環境情報学部

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

In this paper, we present an automatic adaptive metadata generation system using content analysis of sample images. First, our system screens out improper query images for metadata generation by using CBIR that computes structural similarity between sample images and query images. Second, the system generates metadata by selecting sample indexes attached to the sample images that are structurally similar to query images. Third, the system detects improper metadata and re-generates proper metadata by identifying wrongly selected metadata. Our system has improved metadata generation by 23.5% on recall ratio and 37% on fallout ratio rather than just using the results of content analysis.

本文言語	English
ホスト出版物のタイトル	Proceedings - 2005 Symposium on Applications and the Internet Workshops, SAINT2005
ページ	426-429
ページ数	4
出版ステータス	Published - 2005 12月 1
イベント	2005 Symposium on Applications and the Internet Workshops, SAINT2005 - Trento, Italy 継続期間: 2005 1月 31 → 2005 2月 4

出版物シリーズ

名前	Proceedings - 2005 Symposium on Applications and the Internet Workshops, SAINT2005
巻	2005

Other

Other	2005 Symposium on Applications and the Internet Workshops, SAINT2005
国/地域	Italy
City	Trento
Period	05/1/31 → 05/2/4

ASJC Scopus subject areas

工学（全般）

他のファイルとリンク

引用スタイル

Sasaki, H & Kiyoki, Y 2005, Automatic adaptive metadata generation for image retrieval. in Proceedings - 2005 Symposium on Applications and the Internet Workshops, SAINT2005., 1620065, Proceedings - 2005 Symposium on Applications and the Internet Workshops, SAINT2005, vol. 2005, pp. 426-429, 2005 Symposium on Applications and the Internet Workshops, SAINT2005, Trento, Italy, 05/1/31.

@inproceedings{1ca98f46bd5f431980668e4859e9194b,

title = "Automatic adaptive metadata generation for image retrieval",

abstract = "In this paper, we present an automatic adaptive metadata generation system using content analysis of sample images. First, our system screens out improper query images for metadata generation by using CBIR that computes structural similarity between sample images and query images. Second, the system generates metadata by selecting sample indexes attached to the sample images that are structurally similar to query images. Third, the system detects improper metadata and re-generates proper metadata by identifying wrongly selected metadata. Our system has improved metadata generation by 23.5% on recall ratio and 37% on fallout ratio rather than just using the results of content analysis.",

author = "Hideyasu Sasaki and Yasushi Kiyoki",

year = "2005",

month = dec,

day = "1",

language = "English",

isbn = "0769522637",

series = "Proceedings - 2005 Symposium on Applications and the Internet Workshops, SAINT2005",

pages = "426--429",

booktitle = "Proceedings - 2005 Symposium on Applications and the Internet Workshops, SAINT2005",

note = "2005 Symposium on Applications and the Internet Workshops, SAINT2005 ; Conference date: 31-01-2005 Through 04-02-2005",

}

TY - GEN

T1 - Automatic adaptive metadata generation for image retrieval

AU - Sasaki, Hideyasu

AU - Kiyoki, Yasushi

PY - 2005/12/1

Y1 - 2005/12/1

N2 - In this paper, we present an automatic adaptive metadata generation system using content analysis of sample images. First, our system screens out improper query images for metadata generation by using CBIR that computes structural similarity between sample images and query images. Second, the system generates metadata by selecting sample indexes attached to the sample images that are structurally similar to query images. Third, the system detects improper metadata and re-generates proper metadata by identifying wrongly selected metadata. Our system has improved metadata generation by 23.5% on recall ratio and 37% on fallout ratio rather than just using the results of content analysis.

AB - In this paper, we present an automatic adaptive metadata generation system using content analysis of sample images. First, our system screens out improper query images for metadata generation by using CBIR that computes structural similarity between sample images and query images. Second, the system generates metadata by selecting sample indexes attached to the sample images that are structurally similar to query images. Third, the system detects improper metadata and re-generates proper metadata by identifying wrongly selected metadata. Our system has improved metadata generation by 23.5% on recall ratio and 37% on fallout ratio rather than just using the results of content analysis.

UR - http://www.scopus.com/inward/record.url?scp=33947145723&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33947145723&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:33947145723

SN - 0769522637

SN - 9780769522630

T3 - Proceedings - 2005 Symposium on Applications and the Internet Workshops, SAINT2005

SP - 426

EP - 429

BT - Proceedings - 2005 Symposium on Applications and the Internet Workshops, SAINT2005

T2 - 2005 Symposium on Applications and the Internet Workshops, SAINT2005

Y2 - 31 January 2005 through 4 February 2005

ER -

Automatic adaptive metadata generation for image retrieval

抄録

出版物シリーズ

Other

ASJC Scopus subject areas

他のファイルとリンク

フィンガープリント

引用スタイル