Presentation 2022-03-11
Impression Estimation Model for Suit Styles Using CNN Features
Kimiaki Shinkai, Iori Tani, Kensuke Tobitani, Miyuki Toga, Noriko Nagata,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this study, propose a method for estimating the impressions evoked by the style (texture and shape) of a suit for the purpose of a bespoke suit (recommendation) service. We collected 3398 images of suits and used Random Forest to model the relationship between the subjective impressions of 25 words assigned by psychological experiments and CNN features (style features and content features) obtained from the images. The correlation coefficients between the subjective impression scores of the untrained data and the estimated impression scores calculated from the CNN features are obtained from the 9-fold cross-validation, and the results show moderately positive values, confirming the effectiveness of the proposed method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) fashion / suit / CNN / style feature / content feature / impression estimation
Paper # IMQ2021-69,IE2021-131,MVE2021-98
Date of Issue 2022-03-02 (IMQ, IE, MVE)

Conference Information
Committee CQ / IMQ / MVE / IE
Conference Date 2022/3/9(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Online (Zoom)
Topics (in Japanese) (See Japanese page)
Topics (in English) Media of five senses, Multimedia, Media experience, Picture codinge, Image media quality, Network,quality and reliability, etc
Chair Jun Okamoto(NTT) / Kenya Uomori(Osaka Univ.) / Masayuki Ihara(RIKEN) / Kazuya Kodama(NII)
Vice Chair Takefumi Hiraguri(Nippon Inst. of Tech.) / Gou Hasegawa(Tohoku Univ.) / Mitsuru Maeda(Canon) / Kiyoshi Kiyokawa(NAIST) / Hiroyuki Bandoh(NTT) / Toshihiko Yamazaki(Univ. of Tokyo)
Secretary Takefumi Hiraguri(NTT) / Gou Hasegawa(Ritsumeikan Univ.) / Mitsuru Maeda(Nagoya Univ.) / Kiyoshi Kiyokawa(NTT) / Hiroyuki Bandoh(Oosaka Inst. of Tech.) / Toshihiko Yamazaki(NTT)
Assistant Yoshiaki Nishikawa(NEC) / Ryoichi Kataoka(KDDI Research) / Kimiko Kawashima(NTT) / Masato Tsukada(NEC) / Takashi Yamazoe(Seikei Univ.) / Naoya Isoyama(NAIST) / Takenori Hara(DNP) / Mitsuhiro Goto(NTT) / Shunsuke Iwamura(NHK) / Shinobu Kudo(NTT)

Paper Information
Registration To Technical Committee on Communication Quality / Technical Committee on Image Media Quality / Technical Committee on Media Experience and Virtual Environment / Technical Committee on Image Engineering
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Impression Estimation Model for Suit Styles Using CNN Features
Sub Title (in English)
Keyword(1) fashion
Keyword(2) suit
Keyword(3) CNN
Keyword(4) style feature
Keyword(5) content feature
Keyword(6) impression estimation
1st Author's Name Kimiaki Shinkai
1st Author's Affiliation Kwansei Gakuin University(Kwansei Gakuin Univ.)
2nd Author's Name Iori Tani
2nd Author's Affiliation Kobe University(Kobe Univ.)
3rd Author's Name Kensuke Tobitani
3rd Author's Affiliation University of Nagasaki(Univ. of Nagasaki)
4th Author's Name Miyuki Toga
4th Author's Affiliation Kwansei Gakuin University(Kwansei Gakuin Univ.)
5th Author's Name Noriko Nagata
5th Author's Affiliation Kwansei Gakuin University(Kwansei Gakuin Univ.)
Date 2022-03-11
Paper # IMQ2021-69,IE2021-131,MVE2021-98
Volume (vol) vol.121
Number (no) IMQ-420,IE-422,MVE-423
Page pp.pp.312-317(IMQ), pp.312-317(IE), pp.312-317(MVE),
#Pages 6
Date of Issue 2022-03-02 (IMQ, IE, MVE)