Abstract
Microscopic impurities can contaminate tea during production, processing, and packaging. Current technologies remove only visible contaminants, leaving microscopic foreign objects that compromise tea quality, and reliable detection methods remain lacking. To address this challenge, we propose YOLOv11-PFT, an improved deep learning model based on YOLOv11, enhanced with Powerful-IoU loss, FasterNet, and Triple Attention modules to boost detection accuracy, reduce model size, and improve feature extraction. The resulting lightweight model achieves 99.16% detection accuracy for microscopic tea contaminants, with Precision, Recall, F1 score, and mAP all near 98.7–99.2%, GFLOPs of 5.5, inference speed of 340.6 FPS, and a model size of only 5.0 MB. It outperforms seven benchmark models in accuracy. YOLOv11-PFT offers an effective solution for microscopic contaminant detection in tea, supporting automation in food safety, intelligent quality control, and edge-device deployment in agriculture.
Similar content being viewed by others
Data availability
Data presented in this study are available on request from the corresponding author.
References
Valavanidis, A. Tea, the most popular beverage worldwide, is beneficial to human health. Studies on antioxidant polyphenolic constituents and epidemiological evidence for disease prevention. Sci. Rev. 3, 1–35 (2019).
Toai, D. B. Unveiling the dynamics of Chinese tea exports: a comprehensive analysis of black and green tea from 2018 to 2024. Econ. Manag. Innov. 2, 47–56 (2025).
Lu, W. Tea culture in China: tradition meets modernity. J. Dev. Soc. Sci. 5, 232–241 (2024).
Fu, C. et al. A study on the sustainable development of the Yunnan tea industry under the pressure of China’s Tea Inventory. Preprint at https://doi.org/10.21203/rs.3.rs-4946923 (2024).
Pan, S. Y. et al. Tea and tea drinking: China’s outstanding contributions to the mankind. Chin. Med. 17, 27 (2022).
Wiseman, S. A., Balentine, D. A. & Frei, B. Antioxidants in tea. Crit. Rev. Food Sci. Nutr. 37, 705–718 (1997).
Huda, H. S. A. et al. Exploring the ancient roots and modern global brews of tea and herbal beverages: a comprehensive review of origins, types, health benefits, market dynamics, and future trends. Food Sci. Nutr. 12, 6938–6955 (2024).
Xing, D. et al. Microplastics in tea from planting to the final tea product: traceability, characteristics and dietary exposure risk analysis. Food Chem. 455, 139636 (2024).
Xiang, T. et al. Microscopic Raman-based rapid detection of submicron/nano polypropylene plastics in tea and tea beverages. Food Chem. 454, 139657 (2024).
Lee, D. H. et al. Green tea extracts rich in epicatechins inducing aggregation and inhibiting absorption of amine surface functionalized polystyrene microplastics in vitro mimick system. J. Hazard. Mater. Adv. 15, 100437 (2024).
Jayasingha, H. et al. Fluoride in tea: accumulation, dietary exposure, and future strategies for risk mitigation in food safety; a scoping review. Crit. Rev. Food Sci. Nutr. 12, 1–14 (2025).
Wu, Q., Zheng, Q., He, Y., Chen, Q. & Yang, H. Emerging nanoagents for medical X-ray imaging. Anal. Chem. 95, 33–48 (2023).
Payne, K., O’Bryan, C. A., Marcy, J. A. & Crandall, P. G. Detection and prevention of foreign material in food: a review. Heliyon 9, 9 (2023).
Sun, X., Li, J., Shen, Y. & Li, W. Non-destructive detection of insect foreign bodies in finishing tea product based on terahertz spectrum and image. Front. Nutr. 8, 757491 (2021).
Saeidan, A., Khojastehpour, M., Golzarian, M. R., Mooenfard, M. & Khan, H. A. Detection of foreign materials in cocoa beans by hyperspectral imaging technology. Food Control 129, 108242 (2021).
Kotwaliwale, N. et al. X-ray imaging methods for internal quality evaluation of agricultural produce. J. Food Sci. Technol. 51, 1–15 (2014).
Reutov, Y. Y. & Pudov, V. I. Experience in developing and using metal detectors for medical purposes. Russ. J. Nondestr. Test. 59, 1306–1314 (2023).
Guo, Y. et al. Identification and sorting of impurities in tea using spectral vision. LWT. 205, 116519 (2024).
Wang, C. Y. & Liao, H. Y. M. YOLOv1 to YOLOv10: the fastest and most accurate real-time object detection systems. APSIPA Trans. Signal Inf. Process. 13, 1 (2024).
Rokhva, S. & Teimourpour, B. Accurate & real-time food classification through the synergistic integration of EfficientNetB7, CBAM, transfer learning, and data augmentation. Food Humanit. 4, 100492 (2025).
Deng, L., Li, J. & Han, Z. Online defect detection and automatic grading of carrots using computer vision combined with deep learning methods. LWT 149, 111832 (2021).
Fan, S. et al. On line detection of defective apples using computer vision system combined with deep learning methods. J. Food Eng. 286, 110102 (2020).
Liao, H. et al. A lightweight algorithm for potato defect detection. Smart Agric. Technol. 10, 100849 (2025).
Sun, Y. et al. TDDet: a novel lightweight and efficient tea disease detector. Comput. Electron. Agric. 237, 110481 (2025).
Huang, J., Wang, X., Jin, C., Cheein, F. A. & Yang, X. Estimation of the orientation of potatoes and detection bud eye position using potato orientation detection you only look once with fast and accurate features for the movement strategy of intelligent cutting robots. Eng. Appl. Artif. Intell. 142, 109923 (2025).
Ding, Z., Wang, M., Hu, B., Chen, Z. & Dong, C. Impurity detection of premium green tea based on improved lightweight deep learning model. Food Res. Int. 200, 115516 (2025).
Wang, Z. et al. Detection of small foreign objects in Pu-erh sun-dried green tea: an enhanced YOLOv8 neural network model based on deep learning. Food Control 168, 110890 (2025).
Rong, D., Wang, H., Xie, L., Ying, Y. & Zhang, Y. Impurity detection of juglans using deep learning and machine vision. Comput. Electron. Agric. 178, 105764 (2020).
Rashed, M., Fakhry, S. & Satour, R. Revolutionizing food quality with machine vision and machine learning techniques. In Food in the Metaverse and Web 3.0 Era: Intersecting Food, Technology, and Culture. IGI Global Scientific Publishing. 71–124 (2025).
Rokhva, S., Teimourpour, B. & Soltani, A. H. Computer vision in the food industry: accurate, real-time, and automatic food recognition with pretrained MobileNetV2. Food Humanit. 3, 100378 (2024).
Shi, G. Y. et al. 1D gradient-weighted class activation mapping, visualizing decision process of convolutional neural network-based models in spectroscopy analysis. Anal. Chem. 95, 9959–9966 (2023).
Hou, M. et al. Innovations in seafood freshness quality: non-destructive detection of freshness in Litopenaeus vannamei using the YOLO-shrimp model. Food Chem. 463, 141192 (2025).
Sirisha, U., Praveen, S. P., Srinivasu, P. N., Barsocchi, P. & Bhoi, A. K. Statistical analysis of design aspects of various YOLO-based deep learning models for object detection. Int. J. Comput. Intell. Syst. 16, 126 (2023).
Kurniawan, H. et al. Advanced detection of foreign objects in fresh-cut vegetables using YOLOv5. LWT 212, 116989 (2024).
Yang, Y., Liu, Z., Huang, M., Zhu, Q. & Zhao, X. Automatic detection of multi-type defects on potatoes using multispectral imaging combined with a deep learning model. J. Food Eng. 336, 111213 (2023).
Xie, T., Li, X., Zhang, X., Hu, J. & Fang, Y. Detection of Atlantic salmon bone residues using machine vision technology. Food Control 123, 107787 (2021).
Wang, S. M. et al. Tea yield estimation using UAV images and deep learning. Ind. Crops Prod. 212, 118358 (2024).
Gazari, A. R., Rokhva, S., Khatibi, T., Noughabi, E. A. & Teimourpour, B. A combination of EDA, machine learning, and artificial neural networks for accurate prediction of heart disease. Ann. Healthc. Syst. Eng. 2, 38–46 (2025).
Rokhva, S. & Teimourpour, B. Artificial intelligence in the food industry: food waste estimation based on computer vision, a brief case study in a University Dining Hall. arXiv preprint arXiv:2507.14662 (2025).
Abbasi, S., Rokhva, S., Farahmand, K., Ghasemi, P. & Shahab, E. Designing sustainable closed-loop supply chain network based on a circular economy approach: under uncertainty during the post-COVID era. Circ. Econ. Sustain. 5, 2229–2271 (2025).
Ding, J. et al. Tea processing steps affect chemical compositions, enzyme activities, and antioxidant and anti-inflammatory activities of coffee leaves. Food Front. 3, 505–516 (2022).
Meina, J. et al. Intercropping tea with flowering Pisum sativum regulates Apolygus lucorum populations and provides ecological benefits. J. Plant Dis. Prot. 132, 106 (2025).
Wang, S. Evaluation of impact of image augmentation techniques on two tasks: window detection and window states detection. Results Eng. 24, 103571 (2024).
Siddique, A. et al. Development of predictive classification models and extraction of signature wavelengths for the identification of spoilage in chicken breast fillets during storage using near infrared spectroscopy. Food Bioprocess. Technol. 18, 933–941 (2025).
Bora, G. J., Saikia, B. & Ansari, R. Detection of honey adulteration using linear regression method. Phys. Front. 1, 137–140 (2025).
Dong, C. & Duoqian, M. Control distance IoU and control distance IoU loss for better bounding box regression. Pattern Recognit. 137, 109256 (2023).
Wang, D. et al. SDS-YOLO: an improved vibratory position detection algorithm based on YOLOv11. Measurement 244, 116518 (2025).
Wang, Z., Lu, X. & Yu, Z. An asymmetric selective kernel network for drone-based vehicle detection to build a high-accuracy vehicle trajectory dataset. Remote Sens. 17, 407 (2025).
Liu, C. et al. Powerful-IoU: more straightforward and faster bounding box regression loss with a nonmonotonic focusing mechanism. Neural Netw. 170, 276–284 (2024).
Chen, J. et al. Run, don’t walk: chasing higher FLOPS for faster neural networks. In Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, BC, Canada, 12021–12031 (2023).
Misra, D., Nalamada, T., Arasanipalai, A. U. & Hou, Q. Rotate to attend: convolutional triplet attention module. In Proc. of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). Waikoloa, HI, USA, 3139–3148 (2021).
Acknowledgements
This research was supported by the following projects: National Natural Science Foundation of China (No. 32460782), Yunnan Tea Industry Artificial Intelligence and Big Data Application Innovation Team (No. 202405AS350025), Yunnan International Joint Laboratory for Intelligent Tea Industry (No. 202403AP140022), Yunnan Basic Research Special Fund (No. 202301AS070083), Sub-project of Yunnan Major Science and Technology Special Program (No. 202302AE09002001), Menghai County Smart Tea Industry Science and Technology Special Mission Team of Yunnan Province (No. 202304BI090013), and Yunnan Patent Innovation and Transformation Talent “Introduction, Cultivation and Use” Project (No. YNZCZH2024001).
Author information
Authors and Affiliations
Contributions
Zejun Wang: conceived the overall design and conceptualization of the study, drafted the manuscript, and completed the final revision; Chun Wang was responsible for the establishment, simulation, and data analysis of the network model; Wenxia Yuan and Xiujuan Deng undertook the collection of the dataset; Houqiao Wang and Tianyu Wu managed the manuscript editing and review revisions; Jinyan Zhao and Weihao Liu undertook external experimental verification; Baijuan Wang provided financial support, project management, and review revisions. All authors have read and approved the final version of the manuscript for publication.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Wang, Z., Wang, C., Yuan, W. et al. Non-destructive detection of micro-impurities in tea using the YOLOv11-PFT model. npj Sci Food (2026). https://doi.org/10.1038/s41538-025-00702-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41538-025-00702-6
