Presentation 2014-03-06
Estimating nutrition information based on semantic segmentation of food image
Kyoko SUDO, Kazuhiko MURASAKI, Yoshiki KAMIYA, Yukinobu TANIGUCHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recognition of food image and the estimation of nutrition information is important for health support services using mobile devices. There is a possibility of improvement of estimation accuracy by segmentation of the region of food objects. In this paper, we propose a method to estimate nutrition information based on the segmentaion and the labeling of the region of food objects by adopting the semi-supervised annotation method. In order to estimate nutrition information such as calorie, the appearance frequency of labels which are given to the small regions is learned by regression analysis. The experiment show that the value of calorie is better estimated by using labels of segmented region than directly using the color feature for regression.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) food image / recipe / ingredients / segmentation
Paper # IMQ2013-38,IE2013-147,MVE2013-76
Date of Issue

Conference Information
Committee MVE
Conference Date 2014/2/27(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 Media Experience and Virtual Environment (MVE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Estimating nutrition information based on semantic segmentation of food image
Sub Title (in English)
Keyword(1) food image
Keyword(2) recipe
Keyword(3) ingredients
Keyword(4) segmentation
1st Author's Name Kyoko SUDO
1st Author's Affiliation NTT Media Intelligence Laboratories, Nippon Telegraph and Telephone()
2nd Author's Name Kazuhiko MURASAKI
2nd Author's Affiliation NTT Media Intelligence Laboratories, Nippon Telegraph and Telephone
3rd Author's Name Yoshiki KAMIYA
3rd Author's Affiliation Nagoya Institute of Technology
4th Author's Name Yukinobu TANIGUCHI
4th Author's Affiliation NTT Media Intelligence Laboratories, Nippon Telegraph and Telephone
Date 2014-03-06
Paper # IMQ2013-38,IE2013-147,MVE2013-76
Volume (vol) vol.113
Number (no) 470
Page pp.pp.-
#Pages 4
Date of Issue