An image-based food quality analysis framework driven by large language models
- 27 April 2026
- journal article
- research article
- Published by Royal Society of Chemistry (RSC) in Analytical Methods
- Vol. 18 (17) , 3465-3475
Abstract
LLM-based visual inspection framework with two paths: text-only inference and vision-language inference. A lightweight GUI enables one-click automation. Models are evaluated on ripeness, freshness, and authenticity tasks.Keywords
Funding Information
- National Natural Science Foundation of China (22204049)
- National Natural Science Foundation of China (22574045)
- Education Department of Hunan Province (23A0028)
This publication has 35 references indexed in Scilit:
- Rapid and Non-destructive Identification of American Ginseng via a Self-supervised Computer Vision ApproachJournal of Analysis and Testing, 2025
- LUMIR: an LLM-driven unified agent framework for multi-task infrared spectroscopy reasoningAnalytica Chimica Acta, 2025
- Smartphone video imaging: A versatile, low-cost technology for food authenticationFood Chemistry, 2024
- Applications of Artificial Intelligence and Machine Learning in Food Quality Control and Safety AssessmentFood Engineering Reviews, 2023
- Rapid detection and prediction model establishment of propachlor residues in food assisted by machine learningJournal of Food Measurement and Characterization, 2023
- Prompt Engineering with ChatGPT: A Guide for Academic WritersAnnals of Biomedical Engineering, 2023
- VegNet: Dataset of vegetable quality images for machine learning applicationsData in Brief, 2022
- Prediction of total volatile basic nitrogen (TVB-N) and 2-thiobarbituric acid (TBA) of smoked chicken thighs using computer vision during storage at 4 °CComputers and Electronics in Agriculture, 2022
- Fast Determination of the Rubber Content in Taraxacum kok-saghyz Fresh Biomass Using Portable Near-Infrared Spectroscopy and Pyrolysis–Gas ChromatographyJournal of Analysis and Testing, 2022
- Analysis of food appearance properties by computer vision applying ellipsoids to colour dataComputers and Electronics in Agriculture, 2013