DataVXAdvanced SciencePaper
journal article·2026-06Open access

Long‐Tea‐CLIP: An Expert‐Level Multimodal AI Framework for Fine‐Grained Green Tea Grading Across Five Sensory Dimensions

Yanqun Xu, Zhengfang Xue, Qing Luo, Xu Liu, Yongquan Xu, Jing Huang, Xingcai Zhang, Xinyuan Zhang, Zhonghua Liu, Zisheng Luo

Advanced Science· Volume 13· Issue 32
Publisher pageOpen full text
Source abstract

Abstract

ABSTRACT 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.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Tea Polyphenols and Effects · Nutritional Studies and Diet · Advanced Chemical Sensor Technologies

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

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 Technology Zhejiang University Hangzhou China

The Rural Development Academy Zhejiang University Hangzhou China

School of Intelligent Systems Science and Engineering Jinan University Zhuhai China

China Tea Science Society Hangzhou China

Tea Research Institute Chinese Academy of Agricultural Sciences Key Laboratory of Tea Biology and Resources Utilization Ministry of Agriculture Hangzhou China

Department of Materials Science and Engineering Stanford University Stanford California USA

Funding

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

References (52)

Show source-provided references
1. Tea and Cancer Prevention
2. 10.1002/advs.20230540510.1002/advs.202305405 ↗
3. 10.1038/s41477‐023‐01565‐z10.1038/s41477‐023‐01565‐z ↗
4. 10.1016/j.spc.2021.04.01910.1016/j.spc.2021.04.019 ↗
5. 10.1016/j.biocel.2011.04.00210.1016/j.biocel.2011.04.002 ↗
6. 10.1007/s11694‐021‐01232‐x10.1007/s11694‐021‐01232‐x ↗
7. 10.1016/j.foodchem.2021.13009610.1016/j.foodchem.2021.130096 ↗
8. 10.1016/j.foodcont.2020.10748510.1016/j.foodcont.2020.107485 ↗
9. Mauger M. · 2022 · 17
10. 10.1038/s41467-023-36017-x10.1038/s41467-023-36017-x ↗
11. 10.1038/s41467‐024‐52416‐010.1038/s41467‐024‐52416‐0 ↗
12. 10.32604/cmc.2020.01294510.32604/cmc.2020.012945 ↗
13. 10.1002/advs.20240706010.1002/advs.202407060 ↗
14. 10.1007/s00521‐021‐05827‐910.1007/s00521‐021‐05827‐9 ↗
15. 10.1038/s42256‐023‐00624‐610.1038/s42256‐023‐00624‐6 ↗
16. 10.1016/j.indcrop.2023.11712710.1016/j.indcrop.2023.117127 ↗
17. 10.1038/s43588‐024‐00679‐410.1038/s43588‐024‐00679‐4 ↗
18. K.He X.Zhang S.Ren andJ.Sun “Deep Residual Learning for Image Recognition ” inProceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2016) 770–778 https://doi.org/10.1109/CVPR.2016.90.10.1109/CVPR.2016.90 ↗
19. 10.1214/aos/101320345110.1214/aos/1013203451 ↗
20. A.Zhang Z. C.Lipton M.Li andA. J.Smola “Dive into Deep Learning ”arXiv preprint:2106.11342 2021 https://doi.org/10.48550/arXiv.2106.11342.
21. A.Radford J. W.Kim andC.Hallacy “Learning Transferable Visual Models From Natural Language Supervision ” inInternational Conference on Machine Learning(PMLR 2021) 8748.
22. 10.1111/jfpe.1430310.1111/jfpe.14303 ↗
23. 10.3390/foods1123380010.3390/foods11233800 ↗
24. 10.1002/fsn3.148410.1002/fsn3.1484 ↗
25. 10.1038/s41538‐023‐00187‐110.1038/s41538‐023‐00187‐1 ↗
26. 10.1016/j.foodres.2022.11151210.1016/j.foodres.2022.111512 ↗
27. 10.1016/j.jfca.2016.12.01110.1016/j.jfca.2016.12.011 ↗
28. 10.1016/j.foodcont.2024.11036110.1016/j.foodcont.2024.110361 ↗
29. Z.Shan Y.Zhang Q.Yang et al. “Contrastive Pre‐Training With Multi‐View Fusion for No‐Reference Point Cloud Quality Assessment ” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition(IEEE 2024) 25942–25951.10.1109/CVPR52733.2024.02451 ↗
30. S.MoandP.Morgado “Unveiling the Power of Audio‐Visual Early Fusion Transformers With Dense Interactions Through Masked Modeling ” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition(IEEE 2024) 27186–27196.10.1109/CVPR52733.2024.02567 ↗
31. Z.Lv Y.Wei W.Zuo andK.‐Y. K.Wong “PLACE: Adaptive Layout‐Semantic Fusion for Semantic Image Synthesis ” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition(IEEE 2024) 9264–9274.10.1109/CVPR52733.2024.00885 ↗
32. 10.1016/j.compag.2024.10946210.1016/j.compag.2024.109462 ↗
33. 10.1016/j.fochx.2023.10092410.1016/j.fochx.2023.100924 ↗
34. 10.1002/advs.20230897610.1002/advs.202308976 ↗
35. 10.1016/j.jfca.2023.10592410.1016/j.jfca.2023.105924 ↗
36. 10.1038/s41598‐024‐54389‐y10.1038/s41598‐024‐54389‐y ↗
37. 10.3389/fsufs.2023.117254310.3389/fsufs.2023.1172543 ↗
38. 10.1016/j.foodchem.2022.13513510.1016/j.foodchem.2022.135135 ↗
39. 10.1177/0020294022109097310.1177/00202940221090973 ↗
40. 10.3390/s1705100710.3390/s17051007 ↗
41. 10.3390/chemosensors1107035410.3390/chemosensors11070354 ↗
42. 10.1016/j.cjac.2021.11.00810.1016/j.cjac.2021.11.008 ↗
43. Gong S. Y. · 2018
44. Zhao Y. · 2021
45. S. C.Wong A.Gatt V.Stamatescu andM. D.McDonnell “Understanding Data Augmentation for Classification: When to Warp ” in2016 International Conference on Digital Image Computing: Techniques and Applications(DICTA IEEE 2016) 1–6.10.1109/DICTA.2016.7797091 ↗
46. 10.1016/j.foodchem.2022.13221710.1016/j.foodchem.2022.132217 ↗
47. 10.1021/acs.jafc.2c0545610.1021/acs.jafc.2c05456 ↗
48. 10.1038/s43588‐024‐00682‐910.1038/s43588‐024‐00682‐9 ↗
49. 10.1016/j.fishres.2024.10716110.1016/j.fishres.2024.107161 ↗
50. 10.1039/D1NR06195J10.1039/D1NR06195J ↗
51. 10.1023/B:Stco.0000035301.49549.8810.1023/B:Stco.0000035301.49549.88 ↗
52. T. Q.ChenandC.Guestrin “XGBoost: A Scalable Tree Boosting System ” inProceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining(Association for Computing Machinery 2016) 785–794.10.1145/2939672.2939785 ↗