Mixed deep learning and natural language processing method for fake-food image recognition and standardization to help automated dietary assessment.

Journal: Public health nutrition

PMID: 29623869

Abstract

OBJECTIVE: The present study tested the combination of an established and a validated food-choice research method (the 'fake food buffet') with a new food-matching technology to automate the data collection and analysis.

Authors

Simon Mezgec

Information and Communication Technologies, Jožef Stefan International Postgraduate School, Jamova Cesta 39, 1000 Ljubljana, Slovenia. simon.mezgec@gmail.com.
Tome Eftimov

Jožef Stefan Institute, Ljubljana, Slovenia.
Tamara Bucher

3Institute of Food,Nutrition and Health (IFNH),ETH Zürich,Zürich,Switzerland.
Barbara Koroušić Seljak

Jožef Stefan Institute, Ljubljana, Slovenia.

Keywords

Algorithms Deep Learning Diet Records Food Preferences Humans Image Processing, Computer-Assisted Natural Language Processing Nutrition Assessment

External Resources

View on PubMed Access via DOI PubMed (29623869)

Mixed deep learning and natural language processing method for fake-food image recognition and standardization to help automated dietary assessment.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals