AI-assisted, transparent, developed by researchers, and used by research groups and medical cohorts internationally: MyFoodRepo is a full-stack system for professional nutrition tracking.
MyFoodRepo is built for research studies. Onboard participants, annotate their data, communicate with participants, and export the collected data in real-time, all from an easy-to-use web interface.
Rooted in science and engineering, the MyFoodRepo system is developed and maintained by a research team studying nutrition. It is continuously improved to meet the needs of study participants and researchers.
Douae El Fatouhi, Harris Héritier, Chloé Allémann, Laurent Malisoux, Nasser Laouali, Jean-Pierre Riveline, Marcel Salathé, Guy Fagherazzi
The Food Recognition Benchmark: Using Deep Learning to Recognize Food in Images
Sharada Prasanna Mohanty, Gaurav Singhal, Eric Antoine Scuccimarra, Djilani Kebaili, Harris Héritier, Victor Boulanger, Marcel Salathé
FoodRepo: An Open Food Repository of Barcoded Food Products
Gianrocco Lazzari, Yannis Jaquet, Djilani J Kebaili, Laura Symul, Marcel Salathé
Performance of the Digital Dietary Assessment Tool MyFoodRepo
Claire Zuppinger, Patrick Taffé, Gerrit Burger, Wafa Badran-Amstutz, Tapio Niemi, Clémence Cornuz, Fabiën N. Belle, Angeline Chatelan, Muriel Paclet Lafaille, Murielle Bochud, Semira Gonseth Nusslé
From the mobile app to the AI algorithms, from the web backend to the barcoded food database, all parts of the system are tightly integrated, coming from the same source.
The MyFoodRepo system is both leveraging and generating open data, and critical parts of the system such as AI algorithms are available as open source code.
© Copyright 2017–2023 MyFoodRepo. A project by the Digital Epidemiology Lab at EPFL, with support from Kristian Gerhard Jebsen Foundation, the Seerave Foundation and Leenaards Foundation.