Presentation 2016-02-29
An effect of the automatic tagging by meta-data for image retrieval
Arinori Takahashi, Reiko Hishiyama,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) One of multimedia content acquisition method on the Web is using tag which is describe of content. Different words is tagged to same subject or nature. In addition, tags are provided in specific language from the content. This model proposes automatically tagging which is insufficient for content describe in multilanguage. Our experimental evaluations showed that users could obtain more appropriate images with this method. As a result the following point has been clarified. Improving the search accuracy by assigning more appropriate tags in the image database. After identifying the proper characteristic color of an image, it was possible to readily obtain positive images via automatic tagging by extracting the color of an image as metadata.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) image retrieval / automatic tagging / language grid
Paper # AI2015-52
Date of Issue 2016-02-22 (AI)

Conference Information
Committee AI
Conference Date 2016/2/29(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Kyoto Univ.
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Toshiharu Sugawara(Waseda Univ.)
Vice Chair Tsunenori Mine(Kyushu Univ.) / Daisuke Katagami(Tokyo Polytechnic Univ.)
Secretary Tsunenori Mine(Ritsumeikan Univ.) / Daisuke Katagami(Shizuoka Univ.)
Assistant Yuichi Sei(Univ. of Electro-Comm.)

Paper Information
Registration To Technical Committee on Artificial Intelligence and Knowledge-Based Processing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) An effect of the automatic tagging by meta-data for image retrieval
Sub Title (in English)
Keyword(1) image retrieval
Keyword(2) automatic tagging
Keyword(3) language grid
1st Author's Name Arinori Takahashi
1st Author's Affiliation Waseda University(Waseda Univ.)
2nd Author's Name Reiko Hishiyama
2nd Author's Affiliation Waseda University(Waseda Univ.)
Date 2016-02-29
Paper # AI2015-52
Volume (vol) vol.115
Number (no) AI-468
Page pp.pp.1-6(AI),
#Pages 6
Date of Issue 2016-02-22 (AI)