Cargando…

Rapid Non-Destructive Analysis of Food Nutrient Content Using Swin-Nutrition

Food non-destructive detection technology (NDDT) is a powerful impetus to the development of food safety and quality. One of the essential tasks of food quality regulation is the non-destructive detection of the food’s nutrient content. However, existing food nutrient NDDT performs poorly in terms o...

Descripción completa

Detalles Bibliográficos
Autores principales: Shao, Wenjing, Hou, Sujuan, Jia, Weikuan, Zheng, Yuanjie
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9656370/
https://www.ncbi.nlm.nih.gov/pubmed/36360043
http://dx.doi.org/10.3390/foods11213429
_version_ 1784829416792129536
author Shao, Wenjing
Hou, Sujuan
Jia, Weikuan
Zheng, Yuanjie
author_facet Shao, Wenjing
Hou, Sujuan
Jia, Weikuan
Zheng, Yuanjie
author_sort Shao, Wenjing
collection PubMed
description Food non-destructive detection technology (NDDT) is a powerful impetus to the development of food safety and quality. One of the essential tasks of food quality regulation is the non-destructive detection of the food’s nutrient content. However, existing food nutrient NDDT performs poorly in terms of efficiency and accuracy, which hinders their widespread application in daily meals. Therefore, this paper proposed an end-to-end food nutrition non-destructive detection method, named Swin-Nutrition, which combined deep learning and NDDT to evaluate the nutrient content of food. The method aimed to fully capture the feature information from the food images and thus accurately estimate the nutrient content. Swin-Nutrition resorted to Swin Transformer, the feature fusion module (FFM), and the nutrient prediction module to evaluate nutrient content. In particular, Swin Transformer acted as the backbone network for feature extraction of food images, and FFM was used to obtain the discriminative feature representation to improve the accuracy of prediction. The experimental results on the Nutrition5k dataset demonstrated the effectiveness and efficiency of our proposed method. Specifically, the mean value of the percentage mean absolute error (PMAE) for calories, mass, fat, carbohydrate, and protein were only 15.3%, 12.5%, 22.1%, 20.8%, and 15.4%, respectively. We hope that our simple and effective method will provide a solid foundation for the research of food NDDT.
format Online
Article
Text
id pubmed-9656370
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-96563702022-11-15 Rapid Non-Destructive Analysis of Food Nutrient Content Using Swin-Nutrition Shao, Wenjing Hou, Sujuan Jia, Weikuan Zheng, Yuanjie Foods Article Food non-destructive detection technology (NDDT) is a powerful impetus to the development of food safety and quality. One of the essential tasks of food quality regulation is the non-destructive detection of the food’s nutrient content. However, existing food nutrient NDDT performs poorly in terms of efficiency and accuracy, which hinders their widespread application in daily meals. Therefore, this paper proposed an end-to-end food nutrition non-destructive detection method, named Swin-Nutrition, which combined deep learning and NDDT to evaluate the nutrient content of food. The method aimed to fully capture the feature information from the food images and thus accurately estimate the nutrient content. Swin-Nutrition resorted to Swin Transformer, the feature fusion module (FFM), and the nutrient prediction module to evaluate nutrient content. In particular, Swin Transformer acted as the backbone network for feature extraction of food images, and FFM was used to obtain the discriminative feature representation to improve the accuracy of prediction. The experimental results on the Nutrition5k dataset demonstrated the effectiveness and efficiency of our proposed method. Specifically, the mean value of the percentage mean absolute error (PMAE) for calories, mass, fat, carbohydrate, and protein were only 15.3%, 12.5%, 22.1%, 20.8%, and 15.4%, respectively. We hope that our simple and effective method will provide a solid foundation for the research of food NDDT. MDPI 2022-10-29 /pmc/articles/PMC9656370/ /pubmed/36360043 http://dx.doi.org/10.3390/foods11213429 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Shao, Wenjing
Hou, Sujuan
Jia, Weikuan
Zheng, Yuanjie
Rapid Non-Destructive Analysis of Food Nutrient Content Using Swin-Nutrition
title Rapid Non-Destructive Analysis of Food Nutrient Content Using Swin-Nutrition
title_full Rapid Non-Destructive Analysis of Food Nutrient Content Using Swin-Nutrition
title_fullStr Rapid Non-Destructive Analysis of Food Nutrient Content Using Swin-Nutrition
title_full_unstemmed Rapid Non-Destructive Analysis of Food Nutrient Content Using Swin-Nutrition
title_short Rapid Non-Destructive Analysis of Food Nutrient Content Using Swin-Nutrition
title_sort rapid non-destructive analysis of food nutrient content using swin-nutrition
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9656370/
https://www.ncbi.nlm.nih.gov/pubmed/36360043
http://dx.doi.org/10.3390/foods11213429
work_keys_str_mv AT shaowenjing rapidnondestructiveanalysisoffoodnutrientcontentusingswinnutrition
AT housujuan rapidnondestructiveanalysisoffoodnutrientcontentusingswinnutrition
AT jiaweikuan rapidnondestructiveanalysisoffoodnutrientcontentusingswinnutrition
AT zhengyuanjie rapidnondestructiveanalysisoffoodnutrientcontentusingswinnutrition