Contents Science Lab

Project: Food attractiveness measurements

In recent years, the number of food photos posted on the Web has increased due to the spread of cooking recipe sites and SNS. It is desirable that food photos posted on the Web look delicious, but it is not always easy to take them.

In our research, we develop methods of estimating the attractiveness of food photography, that is, the degree to which the photographed food looks delicious. This is thought to be an assistive technology for taking delicious food using a smartphone.

We use subjective experiment with students to evaluate the preference of different food images, including gaze information during the judging of attractiveness.

Main project members

Akinori Sato

Finished Master in AY2018

Kazuma Takahashi

Finished Master in AY2016

Dr. Keisuke Doman

Invited Associate Professor (Chukyo University)

Recent publications

Estimation of the attractiveness of food photography based on image features

Kazuma Takahashi, Tatsumi Hattori, Keisuke Doman, Yasutomo Kawanishi, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase
IEICE Trans. on Information and Systems, vol.E102-D, no.8, pp.1590-1593, August 2019.

Gaze-inspired learning for estimating the attractiveness of a food photo

Akinori Sato, Takatsugu Hirayama, Keisuke Doman, Yasutomo Kawanishi, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase
Proc. 20th IEEE Int. Symposium on Multimedia (ISM2018), pp.36-43, The Splendor Hotel Taichung (Taichung, Taiwan), December 2018.

Attractiveness estiamtionn method of food photos using gaze information (in Japanese)

Akinori Sato, Takatsugu Hirayama, Keisuke Doman, Yasutomo Kawanishi, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase
IEICE SIG Attractiveness Computing Symposium 2018, Osaka Inst. of Tech., Umeda campus, September 2018.

Estimating the attractiveness of a food photo using a Convolutional Neural Network (in Japanese)

Akinori Sato, Keisuke Doman, Takatsugu Hirayama, Ichiro Ide, Yasutomo Kawanishi, Daisuke Deguchi, Hiroshi Murase
IEICE Tech. Rep. Media Experience and Virtual Environment, MVE2017-32, Kitami Institute of Technology, October 2017.

A food image dataset tagged with attractiveness scores according to view-points (in Japanese)

Ichiro Ide, Kazuma Takahashi, Keisuke Doman, Yasutomo Kawanishi, Takatsugu Hirayama, Daisuke Deguchi, Hiroshi Murase
Proc. 2017 Electric / Electronic / Information Engineering Related Society Tokai Sectors Joint Convention, Po1-25, Nagoya Univ., September 2017.

A food image dataset tagged with attractiveness scores according to view-points (in Japanese)

Ichiro Ide, Kazuma Takahashi, Keisuke Doman, Yasutomo Kawanishi, Takatsugu Hirayama, Daisuke Deguchi, Hiroshi Murase
IEICE SIG Attractiveness Computing Inauguration Symposium, Chiba University, Nishi-Chiba Campus, September 2017.

Improvement of an attractiveness of food photos by using gaze information during preference experiment (in Japanese)

Akinori Sato, Takatsugu Hirayama, Keisuke Doman, Yasutomo Kawanishi, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase
Proc. 2017 Electric / Electronic / Information Engineering Related Society Tokai Sectors Joint Convention, G3-4, Nagoya Univ., September 2017.

Estimation of the attractiveness of food photography focusing on main ingredients

Kazuma Takahashi, Keisuke Doman, Yasutomo Kawanishi, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase
Proc. 9th Workshop on Cooking and Eating Activities (CEA2017) in conjunction with IJCAI2017, pp.1-6, RMIT Univ. (Melbourne, VIC, Australia), August 2017.

TBA (in Japanese)

Akinori Sato, Takatsugu Hirayama, Kazuma Takahashi, Keisuke Doman, Yasutomo Kawanishi, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase
IPSJ Tech. Rep. Computer Vision and Image Media, 2017-CVIM-207-36, Nagoya Univ., May 2017.

Improvement of an attractiveness estimation method for food photos considering the appearance of main ingredients (in Japanese)

Kazuma Takahashi, Keisuke Doman, Yasutomo Kawanishi, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase
IEICE Tech. Rep. Multimedia and Virtual Environment, MVE2016-60, Kyushu Univ. Ohashi Campus, March 2017.

Accuracy improvement of food photo attractiveness estimation based on consideration of image features (in Japanese)

Kazuma Takahashi, Keisuke Doman, Yasutomo Kawanishi, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase
IEICE Tech. Rep. Multimedia and Virtual Environment, MVE2016-12, Lake Shikotsu Marukoma Onsen, October 2016.

TBA (in Japanese)

Kazuma Takahashi, Keisuke Doman, Takatsugu Hirayama, Yasutomo Kawanishi, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase
Meeting on Image Recognition and Understanding (MIRU) 2016, PS1-29, Act City Hamamatsu, August 2016.

A study on estimating the attractiveness of food photography

Kazuma Takahashi, Keisuke Doman, Takatsugu Hirayama, Yasutomo Kawanishi, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase
Proc. First Int Workshop on Attractiveness Computing in Multimedia (ACM 2016) in conjunction with IEEE BigMM2016, pp.444-449, Howard Civil Service International House (Taipei, Taiwan), April 2016.

A study on estimating the attractiveness of food photography composition (in Japanese)

Kazuma Takahashi, Keisuke Doman, Yasutomo Kawanishi, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase
IEICE Tech. Rep. Multimedia and Virtual Environment, MVE2015-23, Otaru City Tourism Products Plaza, October 2015.

A study on analyzing the attractiveness of food photos using image features (in Japanese)

Kazuma Takahashi, Keisuke Doman, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase
Virtual Reality Society of Japan, 16th Meeting of Special Interest Group on Odor, Taste, and Body Information, SBR2015-6, Becchinkan (Kumamoto), June 2015.

TBA (in Japanese)

Kazuma Takahashi, (Hiroshi Murase, Ichiro Ide, Daisuke Deguchi)
2014 IEICE Tokai Sector Bachelor’s Theses Symposium, B3-3, Toyohashi Univ. of Tech., March 2015.