Presentation 2011-05-26
A Preliminary Study on Metadata Estimation Using Similar Images for Clustering Image Search Results
Masaharu HIROTA, Naoki FUKUTA, Shohei YOKOYAMA, Hiroshi ISHIKAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Although metadata are useful to obtain better clustering results on image clustering, some images do not have social tags or metadata about photo-taking conditions. In this paper, we propose a method to estimate those missing metadata of photo images that appear in search results on the Web to make better clustering. We estimate social tags or photo-taking conditions from other images in the image search result. To estimate metadata, our approach does not require another training set that is constructed from other images that are not included in the search result. We demonstrate that the proposed method effectively estimate missing metadata by showing the performance on search problems on a photo sharing site.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) metadata estimation / clustering
Paper # AI2011-5
Date of Issue

Conference Information
Committee AI
Conference Date 2011/5/19(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Artificial Intelligence and Knowledge-Based Processing (AI)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Preliminary Study on Metadata Estimation Using Similar Images for Clustering Image Search Results
Sub Title (in English)
Keyword(1) metadata estimation
Keyword(2) clustering
1st Author's Name Masaharu HIROTA
1st Author's Affiliation Graduate School of Informatics, Shizuoka University()
2nd Author's Name Naoki FUKUTA
2nd Author's Affiliation Department of Computer Science, Faculty of Informatics, Shizuoka University
3rd Author's Name Shohei YOKOYAMA
3rd Author's Affiliation Department of Computer Science, Faculty of Informatics, Shizuoka University
4th Author's Name Hiroshi ISHIKAWA
4th Author's Affiliation Department of Computer Science, Faculty of Informatics, Shizuoka University
Date 2011-05-26
Paper # AI2011-5
Volume (vol) vol.111
Number (no) 70
Page pp.pp.-
#Pages 6
Date of Issue