Presentation 1999/10/22
A Study on an Attractiveness Evaluation Model based on the Physical Features of Image Regions
Shoji Tanaka, Seiji Inokuchi, Yuichi Iwadate,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes an attractiveness evaluation model based on physical features of regions in a picture. This model uses heterogeneity of regions on color, texture, shape, and size, as well as their color, texture, and size as evaluation parameters. These parameters contributed remarkably to the attractiveness in our subjective experiments. The model calculates the level of attractiveness by first merging the parameters with weighted linear combination, and then providing the meged value to the Beta function which is one of the S curve functions. In our experiments, the model could properly estimate the level of attractiveness that human subjects evaluated.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Attractiveness / Attractiveness Estimation / Attractive Region / Attention / Human Vision
Paper # NC99-48
Date of Issue

Conference Information
Committee NC
Conference Date 1999/10/22(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study on an Attractiveness Evaluation Model based on the Physical Features of Image Regions
Sub Title (in English)
Keyword(1) Attractiveness
Keyword(2) Attractiveness Estimation
Keyword(3) Attractive Region
Keyword(4) Attention
Keyword(5) Human Vision
1st Author's Name Shoji Tanaka
1st Author's Affiliation ATR Media Integration & Communications Research Laboratories()
2nd Author's Name Seiji Inokuchi
2nd Author's Affiliation Department of Systems and Human Science, Osaka University
3rd Author's Name Yuichi Iwadate
3rd Author's Affiliation ATR Media Integration & Communications Research Laboratories
Date 1999/10/22
Paper # NC99-48
Volume (vol) vol.99
Number (no) 383
Page pp.pp.-
#Pages 8
Date of Issue