Food image description based on deep-based joint food category, ingredient, and cooking method recognition

Wei Ta Chu; Jia Hsing Lin

doi:10.1109/ICMEW.2017.8026308

Food image description based on deep-based joint food category, ingredient, and cooking method recognition

Wei Ta Chu, Jia Hsing Lin

Department of Computer Science and Information Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

6 Citations (Scopus)

Abstract

Many works have been proposed for food image analysis, such as food recognition and ingredient recognition, in order to facilitate healthcare applications. However, relatively fewer studies have been done on jointly considering multiple factors. In this paper, we think that a food image is better described by not only what food it is but also how it was cooked. We propose neural networks to jointly consider food recognition, ingredient recognition, and cooking method recognition, and verify that recognition performance can be improved by taking multiple factors into account. We collect a food image dataset consisting of clean ingredient information, and demonstrate effectiveness of the proposed recognition models from various viewpoints.

Original language	English
Title of host publication	2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	109-114
Number of pages	6
ISBN (Electronic)	9781538605608
DOIs	https://doi.org/10.1109/ICMEW.2017.8026308
Publication status	Published - 2017 Sept 5
Event	2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017 - Hong Kong, Hong Kong Duration: 2017 Jul 10 → 2017 Jul 14

Publication series

Name	2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017

Other

Other	2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017
Country/Territory	Hong Kong
City	Hong Kong
Period	17-07-10 → 17-07-14

All Science Journal Classification (ASJC) codes

Computer Science Applications
Media Technology

Access to Document

10.1109/ICMEW.2017.8026308

Cite this

Chu, W. T., & Lin, J. H. (2017). Food image description based on deep-based joint food category, ingredient, and cooking method recognition. In 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017 (pp. 109-114). Article 8026308 (2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMEW.2017.8026308

Chu, Wei Ta ; Lin, Jia Hsing. / Food image description based on deep-based joint food category, ingredient, and cooking method recognition. 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 109-114 (2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017).

@inproceedings{a2cbb036305943d9bfb7efcb221728a4,

title = "Food image description based on deep-based joint food category, ingredient, and cooking method recognition",

abstract = "Many works have been proposed for food image analysis, such as food recognition and ingredient recognition, in order to facilitate healthcare applications. However, relatively fewer studies have been done on jointly considering multiple factors. In this paper, we think that a food image is better described by not only what food it is but also how it was cooked. We propose neural networks to jointly consider food recognition, ingredient recognition, and cooking method recognition, and verify that recognition performance can be improved by taking multiple factors into account. We collect a food image dataset consisting of clean ingredient information, and demonstrate effectiveness of the proposed recognition models from various viewpoints.",

author = "Chu, {Wei Ta} and Lin, {Jia Hsing}",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017 ; Conference date: 10-07-2017 Through 14-07-2017",

year = "2017",

month = sep,

day = "5",

doi = "10.1109/ICMEW.2017.8026308",

language = "English",

series = "2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "109--114",

booktitle = "2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017",

address = "United States",

}

Chu, WT & Lin, JH 2017, Food image description based on deep-based joint food category, ingredient, and cooking method recognition. in 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017., 8026308, 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017, Institute of Electrical and Electronics Engineers Inc., pp. 109-114, 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017, Hong Kong, Hong Kong, 17-07-10. https://doi.org/10.1109/ICMEW.2017.8026308

Food image description based on deep-based joint food category, ingredient, and cooking method recognition. / Chu, Wei Ta; Lin, Jia Hsing.
2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 109-114 8026308 (2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Food image description based on deep-based joint food category, ingredient, and cooking method recognition

AU - Chu, Wei Ta

AU - Lin, Jia Hsing

PY - 2017/9/5

Y1 - 2017/9/5

N2 - Many works have been proposed for food image analysis, such as food recognition and ingredient recognition, in order to facilitate healthcare applications. However, relatively fewer studies have been done on jointly considering multiple factors. In this paper, we think that a food image is better described by not only what food it is but also how it was cooked. We propose neural networks to jointly consider food recognition, ingredient recognition, and cooking method recognition, and verify that recognition performance can be improved by taking multiple factors into account. We collect a food image dataset consisting of clean ingredient information, and demonstrate effectiveness of the proposed recognition models from various viewpoints.

AB - Many works have been proposed for food image analysis, such as food recognition and ingredient recognition, in order to facilitate healthcare applications. However, relatively fewer studies have been done on jointly considering multiple factors. In this paper, we think that a food image is better described by not only what food it is but also how it was cooked. We propose neural networks to jointly consider food recognition, ingredient recognition, and cooking method recognition, and verify that recognition performance can be improved by taking multiple factors into account. We collect a food image dataset consisting of clean ingredient information, and demonstrate effectiveness of the proposed recognition models from various viewpoints.

UR - http://www.scopus.com/inward/record.url?scp=85031688086&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85031688086&partnerID=8YFLogxK

U2 - 10.1109/ICMEW.2017.8026308

DO - 10.1109/ICMEW.2017.8026308

M3 - Conference contribution

AN - SCOPUS:85031688086

T3 - 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017

SP - 109

EP - 114

BT - 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017

Y2 - 10 July 2017 through 14 July 2017

ER -

Chu WT, Lin JH. Food image description based on deep-based joint food category, ingredient, and cooking method recognition. In 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 109-114. 8026308. (2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017). doi: 10.1109/ICMEW.2017.8026308

Food image description based on deep-based joint food category, ingredient, and cooking method recognition

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this