Research on Tea Bud Recognition Technology Based on Deep Transfer Learning

ZHU Shaohui; ZHAO Wenju; MA Bohui; YANG Hualin; DENG Fang

doi:10.13305/j.cnki.jts.2025.03.001

Journal of Tea Science >

2025 , Vol. 45 >Issue 3: 522 - 534

DOI: https://doi.org/10.13305/j.cnki.jts.2025.03.001

Research Paper

Research on Tea Bud Recognition Technology Based on Deep Transfer Learning

ZHU Shaohui ,
ZHAO Wenju ,
MA Bohui ,
YANG Hualin ,
DENG Fang

Expand

College of Mechanical and Electrical Engineering, Qingdao University of Science and Technology, Qingdao 266061, China

Received date: 2024-11-19

Revised date: 2024-12-25

Online published: 2025-06-18

Fold

Abstract

To reduce the time cost of repeatedly constructing data samples of tea buds from different seasons and regions, and to improve the accuracy and generalization ability of deep learning models in identifying different tea buds, this paper proposed a small-sample tea bud recognition model based on deep transfer learning, named QY-Yolov7-Tea. By incorporating transfer learning techniques into deep learning, a source domain bud detection model based on Yolov7 was used to obtain pre-trained weights. The model's backbone, neck and detection head are then fine-tuned and frozen, with experiments conducted on different target samples based on the pre-trained weights. The final result is a transfer learning model for tea buds. Experimental results show that, compared with the traditional Yolov7 bud detection model, the deep transfer learning model improves the mean average precision for recognizing tea buds from different seasons and regions by 8.8 percentage points and 15.4 percentage points, respectively, significantly enhancing the model's robustness and recognition capability, and effectively addressing the issue of insufficient training samples.

Key words： tea bud; deep learning; transfer learning; model fine-tuning

Cite this article

ZHU Shaohui , ZHAO Wenju , MA Bohui , YANG Hualin , DENG Fang . Research on Tea Bud Recognition Technology Based on Deep Transfer Learning[J]. Journal of Tea Science, 2025 , 45(3) : 522 -534 . DOI: 10.13305/j.cnki.jts.2025.03.001

References

[1] 常婉秋, 姚宇, 席晓杰, 等. 基于迁移学习和非监督分类的制种玉米遥感识别方法[J]. 农业机械学报, 2024, 55(8): 181-195.
Chang W Q, Yao Y, Xi X J, et al.Remote sensing recognition method for seed production maize based on transfer learning and unsupervised classification[J]. Transactions of the Chinese Society for Agricultural Machinery, 2024, 55(8): 181-195.
[2] 李亚涛. 茶叶采摘机器人的视觉检测与定位技术研究[D]. 杭州: 浙江理工大学, 2022.
Li Y T.Research on the visual detection and localization technology of tea harvesting robot [D]. Hangzhou: Zhejiang Sci-Tech University, 2022.
[3] 李丽, 卢世博, 任浩, 等. 基于改进YOLO v5的复杂环境下桑树枝干识别定位方法[J]. 农业机械学报, 2024, 55(2): 249-257.
Li L, Lu S B, Ren H, et al.Mulberry branch identification and location method based on improved YOLO v5 in complex environment[J]. Transactions of the Chinese Society for Agricultural Machinery, 2024, 55(2): 249-257.
[4] 俞淑燕, 杜晓晨, 冯海林, 等. TTLD-YOLOv7:非结构化环境下茶树病害的检测算法[J]. 茶叶科学, 2024, 44(3): 453-468.
Yu S Y, Du X C, Feng H L, et al.TTLD-YOLOv7: an algorithm for detecting tea diseases in an unstructured environment[J]. Journal of Tea Science, 2024, 44(3): 453-468.
[5] 洪孔林, 吴明晖, 高博, 等. 基于改进YOLOv7-tiny的茶叶嫩芽分级识别方法[J]. 茶叶科学, 2024, 44(1): 62-74.
Hong K L, Wu M H, Gao B, et al.A grading identification method for tea buds based on improved YOLOv7-tiny[J]. Journal of Tea Science, 2024, 44(1): 62-74.
[6] Yosinski J, Clune J, Bengio Y, et al.How transferable are features in deep neural networks? [M]//Ghahramani Z, Welling M, Cortes C, et al. Advances in Neural Information Processing Systems 27, Cambridge, MA: MIT Press, 2014.
[7] Tan C Q, Sun F C, Kong T, et al.A survey on deep transfer learning[C]//Kůrková V, Manolopoulos Y, Hammer B, et al. Artificial Neural Networks and Machine Learning-ICANN 2018. Cham: Springer Cham, 2018: 270-279.
[8] 周立君, 刘宇, 白璐, 等. 一种基于GAN和自适应迁移学习的样本生成方法[J]. 应用光学, 2020, 41(1): 120-126.
Zhou L J, Liu Y, Bai L, et al.Sample generation method based on GAN and adaptive transfer learning[J]. Journal of Applied Optics, 2020, 41(1): 120-126.
[9] 黎英. 迁移学习在医学图像分析中的应用研究综述[J]. 计算机工程与应用, 2021, 57(20): 42-52.
Li Y.Review of application of transfer learning in medical lmage analysis[J]. Computer Engineering and Applications, 2021, 57(20): 42-52.
[10] Khasawneh N, Faouri E, Fraiwan M.Automatic detection of tomato diseases using deep transfer learning[J]. Applied Sciences, 2022, 12(17): 8467. doi: 10.3390/app12178467.
[11] 李平, 马玉琨, 李艳翠, 等. 基于迁移学习的小麦籽粒品种识别研究[J]. 中国农机化学报, 2023, 44(7): 220-228, 280.
Li P, Ma Y K, Li Y C, et al.Study on wheat seed variety identification based on transfer learning[J]. Journal of Chinese Agricultural Mechanization, 2023, 44(7): 220-228, 280.
[12] 付清华. 基于迁移学习的卷积神经网络花卉识别研究[J]. 科学技术创新, 2023(18): 112-115.
Fu Q H.Research on flower recognition of convolution neural network based on transfer learning[J]. Science and Technology Innovation, 2023(18): 112-115.
[13] Kleanthous N, Hussain A, Khan W, et al.Deep transfer learning in sheep activity recognition using accelerometer data[J]. Expert Systems with Applications, 2022, 207: 117925. doi: 10.1016/j.eswa.2022.117925.
[14] 寇旭鹏, 刘帅君, 麻之润. 基于Faster-RCNN的钢带缺陷检测方法[J]. 中国冶金, 2021, 31(4): 77-83.
Kou X P, Liu S J, Ma Z R.Defect detection method of steel strip based on Faster-RCNN[J]. Metallurgy in China, 2021, 31(4): 77-83.
[15] Saeed N, King N, Said Z, et al.Automatic defects detection in CFRP thermograms, using convolutional neural networks and transfer learning[J]. Infrared Physics & Technology, 2019, 102: 103048. doi: 10.1016/j.infrared.2019.103048.
[16] 俞宝库. 基于迁移学习的车轴故障诊断方法研究[D]. 大连: 大连理工大学, 2022.
Yu B K.Research on axle fault diagnosis method based on transfer learning [D]. Dalian: Dalian University of Technology, 2022.
[17] 高伟, 周宸, 郭谋发. 基于改进YOLOv4及SR-GAN的绝缘子缺陷辨识研究[J]. 电机与控制学报, 2021, 25(11): 93-104.
Gao W, Zhou C, Guo M F.Insulator defect identification via improved YOLOv4 and SR-GAN algorithm[J]. Electric Machines and Control, 2021, 25(11): 93-104
[18] 张龙, 胡燕青, 赵丽娟, 等. 多通道信息融合与深度迁移学习的旋转机械故障诊断[J]. 中国机械工程, 2023, 34(8): 966-975.
Zhang L, Hu Y Q, Zhao L J, et al.Multichannel information fusion and deep transfer learning for rotating machinery fault diagnosis[J]. China Mechanical Engineering, 2023, 34(8): 966-975.
[19] Bai Y H, Guo Y X, Zhang Q, et al.Multi-network fusion algorithm with transfer learning for green cucumber segmentation and recognition under complex natural environment[J]. Computers and Electronics in Agriculture, 2022, 194: 106789. doi: 10.1016/j.compag.2022.106789.
[20] Wang L L, Zhao Y J, Liu S B, et al.Precision detection of dense plums in orchards using the improved YOLOv4 model[J]. Frontiers in Plant Science, 2022, 13: 839269. doi: 10.3389/fpls.2022.839269.
[21] 伍子林, 冯德旺, 刘衡伟. 迁移学习在果园病害识别中的应用[J]. 福建电脑, 2023, 39(8): 50-52.
Wu Z L, Feng D W, Liu H W.Application of transfer learning in orchard disease identification[J]. Journal of Fujian Computer, 2023, 39(8): 50-52.
[22] Yao X Z, Lin H F, Bai D, et al.A small target tea leaf disease detection model combined with transfer learning[J]. Forests, 2024, 15(4): 591. doi: 10.3390/f15040591.
[23] 郑子秋, 宋彦, 陈霖, 等. 基于少量标注样本的茶芽目标检测YSVD-Tea算法[J]. 农业机械学报, 2024, 55(8): 301-311.
Zheng Z Q, Song Y, Chen L, et al.YSVD-tea algorithm for tea bud object detection based on few annotated samples[J]. Transactions of the Chinese Society for Agricultural Machinery, 2024, 55(8): 301-311.
[24] Thenmozhi K, Reddy U S.Crop pest classification based on deep convolutional neural network and transfer learning[J]. Computers and Electronics in Agriculture, 2019, 164: 104906. doi: 10.1016/j.compag.2019.104906.
[25] Paymode A S, Malode V B.Transfer learning for multi-crop leaf disease image classification using convolutional neural network VGG[J]. Artificial Intelligence in Agriculture, 2022, 6: 23-33.
[26] Yang B, Lei Y G, Li X, et al.Targeted transfer learning through distribution barycenter medium for intelligent fault diagnosis of machines with data decentralization[J]. Expert Systems with Applications, 2024, 244: 122997. doi: 10.1016/j.eswa.2023.122997.
[27] Razavi M, Mavaddati S, Koohi H.ResNet deep models and transfer learning technique for classification and quality detection of rice cultivars[J]. Expert Systems with Applications, 2024, 247: 123276. doi: 10.1016/j.eswa.2024.123276.

Options

Outlines

模态框（Modal）标题

Abstract

Cite this article

References