goFOOD<sup>TM</sup>: An Artificial Intelligence System for Dietary Assessment
Accurate estimation of nutritional information may lead to healthier diets and better clinical outcomes. We propose a dietary assessment system based on artificial intelligence (AI), named goFOOD<sup>TM</sup>. The system can estimate the calorie and macronutrient content of a meal, on th...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/15/4283 |
| _version_ | 1797560711876968448 |
|---|---|
| author | Ya Lu Thomai Stathopoulou Maria F. Vasiloglou Lillian F. Pinault Colleen Kiley Elias K. Spanakis Stavroula Mougiakakou |
| author_facet | Ya Lu Thomai Stathopoulou Maria F. Vasiloglou Lillian F. Pinault Colleen Kiley Elias K. Spanakis Stavroula Mougiakakou |
| author_sort | Ya Lu |
| collection | DOAJ |
| description | Accurate estimation of nutritional information may lead to healthier diets and better clinical outcomes. We propose a dietary assessment system based on artificial intelligence (AI), named goFOOD<sup>TM</sup>. The system can estimate the calorie and macronutrient content of a meal, on the sole basis of food images captured by a smartphone. goFOOD<sup>TM</sup> requires an input of two meal images or a short video. For conventional single-camera smartphones, the images must be captured from two different viewing angles; smartphones equipped with two rear cameras require only a single press of the shutter button. The deep neural networks are used to process the two images and implements food detection, segmentation and recognition, while a 3D reconstruction algorithm estimates the food’s volume. Each meal’s calorie and macronutrient content is calculated from the food category, volume and the nutrient database. goFOOD<sup>TM</sup> supports 319 fine-grained food categories, and has been validated on two multimedia databases that contain non-standardized and fast food meals. The experimental results demonstrate that goFOOD<sup>TM</sup> performed better than experienced dietitians on the non-standardized meal database, and was comparable to them on the fast food database. goFOOD<sup>TM</sup> provides a simple and efficient solution to the end-user for dietary assessment. |
| first_indexed | 2024-03-10T18:03:24Z |
| format | Article |
| id | doaj.art-a185f259129a4d2cb8aed0d039447b25 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T18:03:24Z |
| publishDate | 2020-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-a185f259129a4d2cb8aed0d039447b252023-11-20T08:41:01ZengMDPI AGSensors1424-82202020-07-012015428310.3390/s20154283goFOOD<sup>TM</sup>: An Artificial Intelligence System for Dietary AssessmentYa Lu0Thomai Stathopoulou1Maria F. Vasiloglou2Lillian F. Pinault3Colleen Kiley4Elias K. Spanakis5Stavroula Mougiakakou6ARTORG Center for Biomedical Engineering Research, University of Bern, 3008 Bern, SwitzerlandARTORG Center for Biomedical Engineering Research, University of Bern, 3008 Bern, SwitzerlandARTORG Center for Biomedical Engineering Research, University of Bern, 3008 Bern, SwitzerlandDivision of Endocrinology, Baltimore Veterans Administration Medical Center, Baltimore, MD 21201, USALuminis Health, Anne Arundel Medical Center, Anne Arundel Medical Group Diabetes and Endocrine Specialists, Annapolis, MD 21401, USADivision of Endocrinology, Baltimore Veterans Administration Medical Center, Baltimore, MD 21201, USAARTORG Center for Biomedical Engineering Research, University of Bern, 3008 Bern, SwitzerlandAccurate estimation of nutritional information may lead to healthier diets and better clinical outcomes. We propose a dietary assessment system based on artificial intelligence (AI), named goFOOD<sup>TM</sup>. The system can estimate the calorie and macronutrient content of a meal, on the sole basis of food images captured by a smartphone. goFOOD<sup>TM</sup> requires an input of two meal images or a short video. For conventional single-camera smartphones, the images must be captured from two different viewing angles; smartphones equipped with two rear cameras require only a single press of the shutter button. The deep neural networks are used to process the two images and implements food detection, segmentation and recognition, while a 3D reconstruction algorithm estimates the food’s volume. Each meal’s calorie and macronutrient content is calculated from the food category, volume and the nutrient database. goFOOD<sup>TM</sup> supports 319 fine-grained food categories, and has been validated on two multimedia databases that contain non-standardized and fast food meals. The experimental results demonstrate that goFOOD<sup>TM</sup> performed better than experienced dietitians on the non-standardized meal database, and was comparable to them on the fast food database. goFOOD<sup>TM</sup> provides a simple and efficient solution to the end-user for dietary assessment.https://www.mdpi.com/1424-8220/20/15/4283carbohydrateproteinfatcalorienutrient estimationcomputer vision |
| spellingShingle | Ya Lu Thomai Stathopoulou Maria F. Vasiloglou Lillian F. Pinault Colleen Kiley Elias K. Spanakis Stavroula Mougiakakou goFOOD<sup>TM</sup>: An Artificial Intelligence System for Dietary Assessment Sensors carbohydrate protein fat calorie nutrient estimation computer vision |
| title | goFOOD<sup>TM</sup>: An Artificial Intelligence System for Dietary Assessment |
| title_full | goFOOD<sup>TM</sup>: An Artificial Intelligence System for Dietary Assessment |
| title_fullStr | goFOOD<sup>TM</sup>: An Artificial Intelligence System for Dietary Assessment |
| title_full_unstemmed | goFOOD<sup>TM</sup>: An Artificial Intelligence System for Dietary Assessment |
| title_short | goFOOD<sup>TM</sup>: An Artificial Intelligence System for Dietary Assessment |
| title_sort | gofood sup tm sup an artificial intelligence system for dietary assessment |
| topic | carbohydrate protein fat calorie nutrient estimation computer vision |
| url | https://www.mdpi.com/1424-8220/20/15/4283 |
| work_keys_str_mv | AT yalu gofoodsuptmsupanartificialintelligencesystemfordietaryassessment AT thomaistathopoulou gofoodsuptmsupanartificialintelligencesystemfordietaryassessment AT mariafvasiloglou gofoodsuptmsupanartificialintelligencesystemfordietaryassessment AT lillianfpinault gofoodsuptmsupanartificialintelligencesystemfordietaryassessment AT colleenkiley gofoodsuptmsupanartificialintelligencesystemfordietaryassessment AT eliaskspanakis gofoodsuptmsupanartificialintelligencesystemfordietaryassessment AT stavroulamougiakakou gofoodsuptmsupanartificialintelligencesystemfordietaryassessment |