Nutrition5k: Towards Automatic Nutritional Understanding of Generic Food
Authors:
- 1 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 8899-8907
Abstract
Understanding the nutritional content of food from visual data is a challenging computer vision problem, with the potential to have a positive and widespread impact on public health. Studies in this area are limited to existing datasets in the field that lack sufficient diversity or labels required for training models with nutritional understanding capability. We introduce Nutrition5k, a novel dataset of 5k diverse, real world food dishes with corresponding video streams, depth images, component weights, and high accuracy nutritional content annotation. We demonstrate the potential of this dataset by training a computer vision algorithm capable of predicting the caloric and macronutrient values of a complex, real world dish at an accuracy that outperforms professional nutritionists. Further we present a baseline for incorporating depth sensor data to improve nutrition predictions. We release Nutrition5k in the hope that it will accelerate innovation in the space of nutritional understanding. The dataset is available at https://github.com/google-research-datasets/Nutrition5k.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Food Recognition: A New Dataset, Experiments, and ResultsIEEE Journal of Biomedical and Health Informatics, 2016
- Food/Non-food Image Classification and Food Categorization using Pre-Trained GoogLeNet Model2016
- Deep-based Ingredient Recognition for Cooking Recipe Retrieval2016
- A comparison of food portion size estimation using geometric models and depth images2016
- Rethinking the Inception Architecture for Computer Vision2016
- Single-View Food Portion Estimation Based on Geometric Models2015
- Im2Calories: Towards an Automated Mobile Vision Food Diary2015
- Menu-Match: Restaurant-Specific Food Logging from Images2015
- Comparison of Known Food Weights with Image-Based Portion-Size Automated Estimation and Adolescents' Self-Reported Portion SizeJournal of Diabetes Science and Technology, 2012
- Adolescents in the United States can identify familiar foods at the time of consumption and when prompted with an image 14 h postprandial, but poorly estimate portionsPublic Health Nutrition, 2011