Presentation 2007-12-14
Ultra high speed image annotation/retrieval method by learning the conceptual relationship between images and labels
Hideki NAKAYAMA, Tatsuya HARADA, Yasuo KUNIYOSHI, Nobuyuki OTSU,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Content-based image recognition and retrieval are challenging problems which have wide application. In this paper, we propose a new method of image annotation and retrieval which far surpasses the current state of the art method based on SML [1] on the standard benchmark database, both in performance and computation speed. Our method uses HLAC (Higher-order Local Auto-Correlation) features and probabilistic canonical correlation analysis to learn the conceptual relationship between images and labels. It's notable that our method performs recognition about 10, 000 times faster than SML. This achievement makes our method highly versatile and practical.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Image Annotation/Retrieval / Probabilistic CCA / Higher-order Local Auto-Correlation Feature
Paper # PRMU2007-147
Date of Issue

Conference Information
Committee PRMU
Conference Date 2007/12/6(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) Ultra high speed image annotation/retrieval method by learning the conceptual relationship between images and labels
Sub Title (in English)
Keyword(1) Image Annotation/Retrieval
Keyword(2) Probabilistic CCA
Keyword(3) Higher-order Local Auto-Correlation Feature
1st Author's Name Hideki NAKAYAMA
1st Author's Affiliation Graduate School of Information Science and Technology, The University of Tokyo()
2nd Author's Name Tatsuya HARADA
2nd Author's Affiliation Graduate School of Information Science and Technology, The University of Tokyo
3rd Author's Name Yasuo KUNIYOSHI
3rd Author's Affiliation Graduate School of Information Science and Technology, The University of Tokyo
4th Author's Name Nobuyuki OTSU
4th Author's Affiliation National Institute of Advanced Industrial Science and Technology
Date 2007-12-14
Paper # PRMU2007-147
Volume (vol) vol.107
Number (no) 384
Page pp.pp.-
#Pages 6
Date of Issue