Presentation 2007-03-16
Image Retrieval with Automatic Labeling with Users' Queries : Growable Search Engine by Users
Shigeru IGUCHI, Hayato YAMANA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes an image retrieval system whose images are labeled and search precision is improved while the system is used. Image retrieval is categorized into two major types: one type is Text-based Image Retrieval(TBIR) which uses keywords(texts) as queries; another type is Content-based Image Retrieval(CBIR) which uses images as queries. TBIR returns images related in linguistics and meaning, CBIR returns images related in look and feel. Moreover, TBIR takes extra effort for labeling images; CBIR does not need labeling, but it does not take into account effective information of keywords. Against that, in this paper, we propose the image retrieval system which uses both keywords and images as queries and returns images related in meaning and look. The feature of this system is that labeling advances and search precision is improved while the system is used. The experimental results show rises of labeling rate, average number of label, precision and F-measure.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) image retrieval / content-based image retrieval(CBIR) / image labeling
Paper # PRMU2006-265
Date of Issue

Conference Information
Committee PRMU
Conference Date 2007/3/9(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Image Retrieval with Automatic Labeling with Users' Queries : Growable Search Engine by Users
Sub Title (in English)
Keyword(1) image retrieval
Keyword(2) content-based image retrieval(CBIR)
Keyword(3) image labeling
1st Author's Name Shigeru IGUCHI
1st Author's Affiliation Graduate Scholl of Science and Engineering, Waseda University()
2nd Author's Name Hayato YAMANA
2nd Author's Affiliation Science and Engineering Waseda, University:National Institute of Informatics
Date 2007-03-16
Paper # PRMU2006-265
Volume (vol) vol.106
Number (no) 606
Page pp.pp.-
#Pages 6
Date of Issue