Long‐Tea‐CLIP: An Expert‐Level Multimodal AI Framework for Fine‐Grained Green Tea Grading Across Five Sensory Dimensions
Advanced Science · 2026-06 · 13 (32)
DOI: 10.1002/advs.202518235 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Science, online erschienen am 27.03.2026. Verfasst von Yanqun Xu und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Food Science & Technology, School of Agriculture and Biology, Shanghai Jiao Tong University, Shanghai, China. Hauptthemen laut MEDLINE: Tea, Artificial Intelligence. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Research and Development Program of Zhejiang Province, National Key Research and Development Program of China, Innovative Research Group Project of the National Natural Science Foundation of China.
Abstract (Originalsprache)
Traditional tea quality evaluation depends on human evaluators, limiting scalability, and consistency. To establish an artificial intelligence (AI)‐assisted framework for comprehensive evaluation of tea quality and detailed assessment of the tea consumption experience, this study aims to develop Long‐Tea‐CLIP (Contrastive Language‐Image Pre‐training), a multimodal tea grading system that combines computer vision and chemoinformatics. It integrates five sensory evaluation dimensions for green tea, using separate submodels for appearance (ResNet‐18), soup color (eXtreme Gradient Boosting (XGBoost)), aroma, infused leaf, and taste (multilayer perceptron (MLP)). A deep network derived from ResNet‐18 integrates dry tea images with seven subdimensions of sensory comments to achieve a refined appearance “grading.” We apply Tip‐CLIP supervised MLP on feature data extraction from infused leaf and chemical data of aroma and taste to enhance accuracy. Submodel outputs are weighted into a unified framework to produce an overall score. Long‐Tea‐CLIP trained on 7763 image‐text pairs from 38 Longjing tea varieties achieves 92% accuracy, indicating its potential to enhance tea quality control and market transparency.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Food Science & Technology, School of Agriculture and Biology, Shanghai Jiao Tong University, Shanghai, China.
- National Research Center of Engineering and Technology for Utilization of Botanical Functional Ingredients, Hunan Agricultural University, Changsha, China.
- College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou, China.
- Laboratory of Agro-Products Postharvest Handling of Ministry of Agriculture and Rural Affairs, Zhejiang Key Laboratory of Agri-Food Resources and High-Value Utilization, Innovation Center for Postharvest Agro-Products T…
- The Rural Development Academy, Zhejiang University, Hangzhou, China.
- School of Intelligent Systems Science and Engineering, Jinan University, Zhuhai, China.
ORCID-Profile: Zisheng Luo
Förderung
- Key Research and Development Program of Zhejiang Province
- National Key Research and Development Program of China
- Innovative Research Group Project of the National Natural Science Foundation of China
- Natural Science Foundation of Hunan Province
Zitieren
APA
Xu, Y., Xue, Z., Luo, Q., Liu, X., Xu, Y., Huang, J., Zhang, X., Zhang, X., Liu, Z., & Luo, Z. (2026). Long‐Tea‐CLIP: An Expert‐Level Multimodal AI Framework for Fine‐Grained Green Tea Grading Across Five Sensory Dimensions. Advanced Science, 13(32). https://doi.org/10.1002/advs.202518235
Vancouver
Xu Y, Xue Z, Luo Q, Liu X, Xu Y, Huang J, et al. Long‐Tea‐CLIP: An Expert‐Level Multimodal AI Framework for Fine‐Grained Green Tea Grading Across Five Sensory Dimensions. Advanced Science. 2026;13(32). doi:10.1002/advs.202518235
BibTeX
@article{Xu2026,
author = {Xu, Yanqun and Xue, Zhengfang and Luo, Qing and Liu, Xu and Xu, Yongquan and Huang, Jing and Zhang, Xingcai and Zhang, Xinyuan and Liu, Zhonghua and Luo, Zisheng},
title = {Long‐Tea‐CLIP: An Expert‐Level Multimodal AI Framework for Fine‐Grained Green Tea Grading Across Five Sensory Dimensions},
journal = {Advanced Science},
year = {2026},
volume = {13},
number = {32},
doi = {10.1002/advs.202518235}
}
EUVIMED