Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Prevalence and social determinants of anxiety and depression among adults in Ghana: a systematic review and meta-analysis protocol.

BMJ open·2024
Same author

Prevention and management of type 2 diabetes mellitus in Uganda and South Africa: Findings from the SMART2D pragmatic implementation trial.

PLOS global public health·2023
Same author

Application of the Theoretical Framework of Acceptability to assess a telephone-facilitated health coaching intervention for the prevention and management of type 2 diabetes.

PloS one·2022
Same author

Glycated haemoglobin and fasting plasma glucose tests in the screening of outpatients for diabetes and abnormal glucose regulation in Uganda: A diagnostic accuracy study.

PloS one·2022
Same author

Intervention Fidelity Focusing on Interaction between Participants and Facilitators in a Telephone-Delivered Health Coaching Intervention for the Prevention and Management of Type 2 Diabetes.

Nutrients·2021
Same author

Food environment interactions after migration: a scoping review on low- and middle-income country immigrants in high-income countries.

Public health nutrition·2021

Related Experiment Video

Updated: Sep 11, 2025

'Boden Food Plate': Novel Interactive Web-based Method for the Assessment of Dietary Intake
04:46

'Boden Food Plate': Novel Interactive Web-based Method for the Assessment of Dietary Intake

Published on: September 18, 2018

7.4K

Image-Based Dietary Assessment Using the Swedish Plate Model: Evaluation of Deep Learning-Based You Only Look Once

Gustav Chrintz-Gath1, Meena Daivadanam2, Laran Matta2

  • 1Department of Informatics and Media, Uppsala University, Box 513, Uppsala, 75120, Sweden, 46 709901474.

JMIR Formative Research
|August 14, 2025
PubMed
Summary
This summary is machine-generated.

YOLOv8 excels at identifying food and estimating portions, outperforming other YOLO versions for dietary guidelines. Further improvements are needed for real-world health applications.

Keywords:
You Only Look Oncedeep learningdietary assessmentfood recognitionmachine learningobject detection models

More Related Videos

Iterative Development of an Innovative Smartphone-Based Dietary Assessment Tool: Traqq
04:54

Iterative Development of an Innovative Smartphone-Based Dietary Assessment Tool: Traqq

Published on: March 19, 2021

4.7K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.3K

Related Experiment Videos

Last Updated: Sep 11, 2025

'Boden Food Plate': Novel Interactive Web-based Method for the Assessment of Dietary Intake
04:46

'Boden Food Plate': Novel Interactive Web-based Method for the Assessment of Dietary Intake

Published on: September 18, 2018

7.4K
Iterative Development of an Innovative Smartphone-Based Dietary Assessment Tool: Traqq
04:54

Iterative Development of an Innovative Smartphone-Based Dietary Assessment Tool: Traqq

Published on: March 19, 2021

4.7K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.3K

Area of Science:

  • Computer Vision
  • Deep Learning
  • Artificial Intelligence

Background:

  • Object detection frameworks like You Only Look Once (YOLO) have advanced image recognition.
  • This study investigates YOLO for food identification and portion estimation.
  • Focus is on alignment with the Swedish plate model for dietary guidelines.

Purpose of the Study:

  • Evaluate and compare YOLOv7, YOLOv8, and YOLOv9 performance.
  • Assess food component detection and proportion estimation.
  • Align AI-driven dietary analysis with public health guidelines.

Main Methods:

  • Developed a custom dataset of 3707 annotated food images (42 classes).
  • Applied preprocessing and data augmentation techniques.
  • Evaluated models using precision, recall, mean average precision, and F1-score.

Main Results:

  • YOLOv8 achieved the highest peak precision (82.4%) and F1-scores, outperforming YOLOv7 and YOLOv9.
  • YOLOv8 demonstrated superior accuracy in food classification and portion estimation.
  • All models struggled with visually similar food items, highlighting recognition complexities.

Conclusions:

  • YOLOv8 shows significant potential for food and portion recognition aligned with dietary models.
  • Further model refinement and diverse training data are crucial for reliable deployment.
  • Enhanced AI tools can support health and dietary monitoring applications.