Presentation 2014-03-13
視線情報と画像特徴に基づく画像の選好推定(テーマセッション,パターン認識・メディア理解における組み合わせと統合,文化の振興と教育)
Yasunori OZAKI, Yusuke SUGANO, Yoichi SATO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this work, we report the result of the estimation for user's image preference by computer with gaze information and image features. Previously, other researchers have proposed to extract image features from gaze positions in the field of activity recognition. Unlike the recognition methods, our goal is to extract image features not only from gaze positions, but also from around gaze positions. We propose a estimation method with machine learning and the features extracted from around gaze positions, to achieve the goal. Our experiment shows that the proposed method improves the estimation accuracy. Thus, we address the importance of peripheral vision in preference recognition.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) image preference / eye movements / machine learning
Paper # PRMU2013-168
Date of Issue

Conference Information
Committee PRMU
Conference Date 2014/3/6(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)
Sub Title (in English)
Keyword(1) image preference
Keyword(2) eye movements
Keyword(3) machine learning
1st Author's Name Yasunori OZAKI
1st Author's Affiliation ()
2nd Author's Name Yusuke SUGANO
2nd Author's Affiliation
3rd Author's Name Yoichi SATO
3rd Author's Affiliation
Date 2014-03-13
Paper # PRMU2013-168
Volume (vol) vol.113
Number (no) 493
Page pp.pp.-
#Pages 6
Date of Issue