An Exploratory Approach to Deriving Nutrition Information of Restaurant Food from Crowdsourced Food Images: Case of Hartford

Deep learning models can recognize the food item in an image and derive their nutrition information, including calories, macronutrients (carbohydrates, fats, and proteins), and micronutrients (vitamins and minerals). This technology has yet to be implemented for the nutrition assessment of restauran...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xiang Chen, Evelyn Johnson, Aditya Kulkarni, Caiwen Ding, Natalie Ranelli, Yanyan Chen, Ran Xu
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	nutrition assessment food image image recognition restaurant food environment FAFH Nutrition. Foods and food supply TX341-641
Acceso en línea:	https://doaj.org/article/8483ce4ee3624e2f8d0ddc8f6c08c300
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:8483ce4ee3624e2f8d0ddc8f6c08c300
record_format	dspace
spelling	oai:doaj.org-article:8483ce4ee3624e2f8d0ddc8f6c08c3002021-11-25T18:37:00ZAn Exploratory Approach to Deriving Nutrition Information of Restaurant Food from Crowdsourced Food Images: Case of Hartford10.3390/nu131141322072-6643https://doaj.org/article/8483ce4ee3624e2f8d0ddc8f6c08c3002021-11-01T00:00:00Zhttps://www.mdpi.com/2072-6643/13/11/4132https://doaj.org/toc/2072-6643Deep learning models can recognize the food item in an image and derive their nutrition information, including calories, macronutrients (carbohydrates, fats, and proteins), and micronutrients (vitamins and minerals). This technology has yet to be implemented for the nutrition assessment of restaurant food. In this paper, we crowdsource 15,908 food images of 470 restaurants in the Greater Hartford region on Tripadvisor and Google Place. These food images are loaded into a proprietary deep learning model (Calorie Mama) for nutrition assessment. We employ manual coding to validate the model accuracy based on the Food and Nutrient Database for Dietary Studies. The derived nutrition information is visualized at both the restaurant level and the census tract level. The deep learning model achieves 75.1% accuracy when compared with manual coding. It has more accurate labels for ethnic foods but cannot identify portion sizes, certain food items (e.g., specialty burgers and salads), and multiple food items in an image. The restaurant nutrition (RN) index is further proposed based on the derived nutrition information. By identifying the nutrition information of restaurant food through crowdsourced food images and a deep learning model, the study provides a pilot approach for large-scale nutrition assessment of the community food environment.Xiang ChenEvelyn JohnsonAditya KulkarniCaiwen DingNatalie RanelliYanyan ChenRan XuMDPI AGarticlenutrition assessmentfood imageimage recognitionrestaurantfood environmentFAFHNutrition. Foods and food supplyTX341-641ENNutrients, Vol 13, Iss 4132, p 4132 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	nutrition assessment food image image recognition restaurant food environment FAFH Nutrition. Foods and food supply TX341-641
spellingShingle	nutrition assessment food image image recognition restaurant food environment FAFH Nutrition. Foods and food supply TX341-641 Xiang Chen Evelyn Johnson Aditya Kulkarni Caiwen Ding Natalie Ranelli Yanyan Chen Ran Xu An Exploratory Approach to Deriving Nutrition Information of Restaurant Food from Crowdsourced Food Images: Case of Hartford
description	Deep learning models can recognize the food item in an image and derive their nutrition information, including calories, macronutrients (carbohydrates, fats, and proteins), and micronutrients (vitamins and minerals). This technology has yet to be implemented for the nutrition assessment of restaurant food. In this paper, we crowdsource 15,908 food images of 470 restaurants in the Greater Hartford region on Tripadvisor and Google Place. These food images are loaded into a proprietary deep learning model (Calorie Mama) for nutrition assessment. We employ manual coding to validate the model accuracy based on the Food and Nutrient Database for Dietary Studies. The derived nutrition information is visualized at both the restaurant level and the census tract level. The deep learning model achieves 75.1% accuracy when compared with manual coding. It has more accurate labels for ethnic foods but cannot identify portion sizes, certain food items (e.g., specialty burgers and salads), and multiple food items in an image. The restaurant nutrition (RN) index is further proposed based on the derived nutrition information. By identifying the nutrition information of restaurant food through crowdsourced food images and a deep learning model, the study provides a pilot approach for large-scale nutrition assessment of the community food environment.
format	article
author	Xiang Chen Evelyn Johnson Aditya Kulkarni Caiwen Ding Natalie Ranelli Yanyan Chen Ran Xu
author_facet	Xiang Chen Evelyn Johnson Aditya Kulkarni Caiwen Ding Natalie Ranelli Yanyan Chen Ran Xu
author_sort	Xiang Chen
title	An Exploratory Approach to Deriving Nutrition Information of Restaurant Food from Crowdsourced Food Images: Case of Hartford
title_short	An Exploratory Approach to Deriving Nutrition Information of Restaurant Food from Crowdsourced Food Images: Case of Hartford
title_full	An Exploratory Approach to Deriving Nutrition Information of Restaurant Food from Crowdsourced Food Images: Case of Hartford
title_fullStr	An Exploratory Approach to Deriving Nutrition Information of Restaurant Food from Crowdsourced Food Images: Case of Hartford
title_full_unstemmed	An Exploratory Approach to Deriving Nutrition Information of Restaurant Food from Crowdsourced Food Images: Case of Hartford
title_sort	exploratory approach to deriving nutrition information of restaurant food from crowdsourced food images: case of hartford
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/8483ce4ee3624e2f8d0ddc8f6c08c300
work_keys_str_mv	AT xiangchen anexploratoryapproachtoderivingnutritioninformationofrestaurantfoodfromcrowdsourcedfoodimagescaseofhartford AT evelynjohnson anexploratoryapproachtoderivingnutritioninformationofrestaurantfoodfromcrowdsourcedfoodimagescaseofhartford AT adityakulkarni anexploratoryapproachtoderivingnutritioninformationofrestaurantfoodfromcrowdsourcedfoodimagescaseofhartford AT caiwending anexploratoryapproachtoderivingnutritioninformationofrestaurantfoodfromcrowdsourcedfoodimagescaseofhartford AT natalieranelli anexploratoryapproachtoderivingnutritioninformationofrestaurantfoodfromcrowdsourcedfoodimagescaseofhartford AT yanyanchen anexploratoryapproachtoderivingnutritioninformationofrestaurantfoodfromcrowdsourcedfoodimagescaseofhartford AT ranxu anexploratoryapproachtoderivingnutritioninformationofrestaurantfoodfromcrowdsourcedfoodimagescaseofhartford AT xiangchen exploratoryapproachtoderivingnutritioninformationofrestaurantfoodfromcrowdsourcedfoodimagescaseofhartford AT evelynjohnson exploratoryapproachtoderivingnutritioninformationofrestaurantfoodfromcrowdsourcedfoodimagescaseofhartford AT adityakulkarni exploratoryapproachtoderivingnutritioninformationofrestaurantfoodfromcrowdsourcedfoodimagescaseofhartford AT caiwending exploratoryapproachtoderivingnutritioninformationofrestaurantfoodfromcrowdsourcedfoodimagescaseofhartford AT natalieranelli exploratoryapproachtoderivingnutritioninformationofrestaurantfoodfromcrowdsourcedfoodimagescaseofhartford AT yanyanchen exploratoryapproachtoderivingnutritioninformationofrestaurantfoodfromcrowdsourcedfoodimagescaseofhartford AT ranxu exploratoryapproachtoderivingnutritioninformationofrestaurantfoodfromcrowdsourcedfoodimagescaseofhartford
_version_	1718410902099722240

An Exploratory Approach to Deriving Nutrition Information of Restaurant Food from Crowdsourced Food Images: Case of Hartford

Ejemplares similares