Presentation 1997/11/28
A Study of Objective Evaluation Method for Image Retrieval Technology based on Shape and Color Features
Kazuyuki KODAMA, Hideyo WAKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose an objective evaluation model for image retrieval technology based on shape and color features. We created this model through (1) similarity rating test for every image pairs (2) and multi-dimensional scaling method, on 32 landscape photographs. Consequently, we could get psychological distances between every two images, and could evaluate image retrieval accuracy, referring to the distances.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) image retrieval / accuracy / objective evaluation model / multi-dimensional scaling / psychological distance
Paper # IE97-97
Date of Issue

Conference Information
Committee IE
Conference Date 1997/11/28(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 Image Engineering (IE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study of Objective Evaluation Method for Image Retrieval Technology based on Shape and Color Features
Sub Title (in English)
Keyword(1) image retrieval
Keyword(2) accuracy
Keyword(3) objective evaluation model
Keyword(4) multi-dimensional scaling
Keyword(5) psychological distance
1st Author's Name Kazuyuki KODAMA
1st Author's Affiliation Telecommunications Advancement Organization of Japan, Tokyo Water Front Research Center()
2nd Author's Name Hideyo WAKI
2nd Author's Affiliation Tokyo Denki University
Date 1997/11/28
Paper # IE97-97
Volume (vol) vol.97
Number (no) 410
Page pp.pp.-
#Pages 6
Date of Issue