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

Improving Translational Accuracy02:07

Improving Translational Accuracy

11.8K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
11.8K
Protein Digestion01:02

Protein Digestion

105.6K
Protein digestion begins in the stomach, where the highly acidic environment can easily disrupt protein structure by exposing the peptide bonds of polypeptide chains. After polypeptide chains are broken into individual amino acids by a series of digestive enzymes, the amino acids are transported to the liver via the bloodstream to produce energy.
105.6K
Health Literacy01:21

Health Literacy

4.1K
Health literacy is an individual's or a community's capacity to comprehend, receive, read, and use relevant healthcare information and services. The World Health Organization (WHO, 2018) defines health literacy as the cognitive and social skills that determine the ability of individuals to gain access to, understand, and use information in ways that promote and maintain good health. As a result, the WHO helps individuals manage long-term health concerns, participate in preventative...
4.1K
Translation01:31

Translation

15.5K
Translation is the process of synthesizing proteins from the genetic information carried by messenger RNA (mRNA). Following transcription, it constitutes the final step in the expression of genes. This process is carried out by ribosomes, complexes of protein and specialized RNA molecules. Ribosomes, transfer RNA (tRNA), and other proteins produce a chain of amino acids—the polypeptide—as the end product of translation.
Translation Produces the Building Blocks of Life
Proteins are...
15.5K
Genetic Lingo01:11

Genetic Lingo

104.5K
Overview
104.5K
Protein Glycosylation01:25

Protein Glycosylation

7.2K
Glycosylation, the most common post-translational modification for proteins, serves diverse functions. Adding sugars to proteins makes the proteins more resistant to proteolytic digestion. Glycosylated proteins can act as markers and receptors to promote cell-cell adhesion. Additionally, they have many essential quality control functions in the cell, such as correct protein folding and facilitating transport of misfolded proteins to the cytosol, which can be degraded.
Glycosylation occurs in...
7.2K

You might also read

Related Articles

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

Sort by
Same author

Rapid Grapevine Health Diagnosis Based on Digital Imaging and Deep Learning.

Plants (Basel, Switzerland)·2024
Same author

Al-Biruni Earth Radius Optimization with Transfer Learning Based Histopathological Image Analysis for Lung and Colon Cancer Detection.

Cancers·2023
Same author

Medical Image Segmentation with Learning Semantic and Global Contextual Representation.

Diagnostics (Basel, Switzerland)·2022
See all related articles

Related Experiment Video

Updated: Sep 10, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

681

Extract Nutritional Information from Bilingual Food Labels Using Large Language Models.

Fatmah Y Assiri1, Mohammad D Alahmadi1, Mohammed A Almuashi2

  • 1Software Engineering Department, College of Computer Science and Engineering, University of Jeddah, Jeddah 21493, Saudi Arabia.

Journal of Imaging
|August 27, 2025
PubMed
Summary

Large language models (LLMs) can extract nutritional data from food labels, but struggle with Arabic text. Post-processing significantly improves accuracy, with GPT-4o outperforming other models for multilingual food label analysis.

Keywords:
LLM (large language model)OCR (optical character recognition)computer vision (CV) text extractionnutrition label

More Related Videos

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
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.6K

Related Experiment Videos

Last Updated: Sep 10, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

681
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
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.6K

Area of Science:

  • Food Science
  • Computational Linguistics
  • Artificial Intelligence

Background:

  • Food product labels are vital for consumers and regulatory bodies like the Food and Drug Administration (FDA).
  • Manual transcription of multilingual food labels is labor-intensive and error-prone.
  • Automating nutritional information extraction from images is crucial for online grocery platforms.

Purpose of the Study:

  • To investigate the efficacy of large language models (LLMs) in extracting nutritional data from multilingual food product labels.
  • To compare the performance of different LLMs (GPT-4o, GPT-4V, Gemini) on English and Arabic food labels.
  • To assess the impact of post-processing techniques on improving extraction accuracy.

Main Methods:

  • A curated dataset of 294 food product labels with 588 transcribed nutritional elements and values in English and Arabic was created.
  • LLMs were employed to extract nutritional information from the label images.
  • Empirical analysis and post-processing techniques were used to evaluate and enhance extraction accuracy.

Main Results:

  • LLMs demonstrated higher accuracy in extracting English nutritional data compared to Arabic.
  • Post-processing techniques substantially improved the overall accuracy of nutritional element and value extraction.
  • GPT-4o achieved superior performance over GPT-4V and Gemini in this task.

Conclusions:

  • LLMs show promise for automating the extraction of nutritional information from food labels.
  • Further advancements in LLM capabilities and post-processing are needed to overcome challenges with multilingual data, particularly Arabic.
  • Optimized LLM-based solutions can enhance data accessibility and accuracy for regulatory compliance and consumer information.