Design criteria of querying interface for visual key image retrieval on mobile devices

Kazushi Okamoto; Kazuhiko Kawamoto; Fangyan Dong; Shinichi Yoshida; Kaoru Hirota

Design criteria of querying interface for visual key image retrieval on mobile devices

Kazushi Okamoto^*, Kazuhiko Kawamoto, Fangyan Dong, Shinichi Yoshida, Kaoru Hirota

^*Corresponding author for this work

Research output: Contribution to conference › Paper › peer-review

1 Citation (Scopus)

Abstract

An evaluation strategy for visual key image retrieval systems is proposed in order to show the design criteria of a querying interface on mobile devices. Indexes (lists of visual keys) generated by different parameters are analyzed, and indexes derived by different visual keys are validated using ArtExplosion 600,000, which contains about 300 semantic categories and over 100,000 natural photos. The result suggests that access to a collection with a visual key can provide one to three relevant images in rank 10 when the number of visual keys is 60, which is the lower limit. In portable devices, which can display 16 visual keys per page, users can at least access a required image by browsing only 4 pages with 60 visual keys, and can use the image for related subsequent queries by using the other image retrieval functions.

Original language	English
Pages	7P
Publication status	Published - 2011
Externally published	Yes
Event	International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2011 - Suzhou, China Duration: 19 Nov 2011 → 23 Nov 2011

Conference

Conference	International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2011
Country/Territory	China
City	Suzhou
Period	19/11/11 → 23/11/11

Keywords

Accuracy
Clustering
Image retrieval
Indexing
Mobile device

Cite this

@conference{7dccef6fd3f44f5fa679f5272d48245b,

title = "Design criteria of querying interface for visual key image retrieval on mobile devices",

abstract = "An evaluation strategy for visual key image retrieval systems is proposed in order to show the design criteria of a querying interface on mobile devices. Indexes (lists of visual keys) generated by different parameters are analyzed, and indexes derived by different visual keys are validated using ArtExplosion 600,000, which contains about 300 semantic categories and over 100,000 natural photos. The result suggests that access to a collection with a visual key can provide one to three relevant images in rank 10 when the number of visual keys is 60, which is the lower limit. In portable devices, which can display 16 visual keys per page, users can at least access a required image by browsing only 4 pages with 60 visual keys, and can use the image for related subsequent queries by using the other image retrieval functions.",

keywords = "Accuracy, Clustering, Image retrieval, Indexing, Mobile device",

author = "Kazushi Okamoto and Kazuhiko Kawamoto and Fangyan Dong and Shinichi Yoshida and Kaoru Hirota",

year = "2011",

language = "English",

pages = "7P",

note = "International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2011 ; Conference date: 19-11-2011 Through 23-11-2011",

}

TY - CONF

T1 - Design criteria of querying interface for visual key image retrieval on mobile devices

AU - Okamoto, Kazushi

AU - Kawamoto, Kazuhiko

AU - Dong, Fangyan

AU - Yoshida, Shinichi

AU - Hirota, Kaoru

PY - 2011

Y1 - 2011

N2 - An evaluation strategy for visual key image retrieval systems is proposed in order to show the design criteria of a querying interface on mobile devices. Indexes (lists of visual keys) generated by different parameters are analyzed, and indexes derived by different visual keys are validated using ArtExplosion 600,000, which contains about 300 semantic categories and over 100,000 natural photos. The result suggests that access to a collection with a visual key can provide one to three relevant images in rank 10 when the number of visual keys is 60, which is the lower limit. In portable devices, which can display 16 visual keys per page, users can at least access a required image by browsing only 4 pages with 60 visual keys, and can use the image for related subsequent queries by using the other image retrieval functions.

AB - An evaluation strategy for visual key image retrieval systems is proposed in order to show the design criteria of a querying interface on mobile devices. Indexes (lists of visual keys) generated by different parameters are analyzed, and indexes derived by different visual keys are validated using ArtExplosion 600,000, which contains about 300 semantic categories and over 100,000 natural photos. The result suggests that access to a collection with a visual key can provide one to three relevant images in rank 10 when the number of visual keys is 60, which is the lower limit. In portable devices, which can display 16 visual keys per page, users can at least access a required image by browsing only 4 pages with 60 visual keys, and can use the image for related subsequent queries by using the other image retrieval functions.

KW - Accuracy

KW - Clustering

KW - Image retrieval

KW - Indexing

KW - Mobile device

UR - http://www.scopus.com/inward/record.url?scp=84874339925&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84874339925

SP - 7P

T2 - International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2011

Y2 - 19 November 2011 through 23 November 2011

ER -

Design criteria of querying interface for visual key image retrieval on mobile devices

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this