数字农科院2.0

Advanced deep learning algorithm for instant discriminating of tea leave stress symptoms by smartphone-based detection

文献类型： 外文期刊

作者： Zhenxiong Huang;Mostafa Gouda;Sitan Ye;Xuechen Zhang;Siyi Li;Tiancheng Wang;Jin Zhang;Xinbei Song;Xiaoli Li;Yong He

作者机构：

关键词： Canopy image;Deep learning models;Infield stress detection;Natural scenes;Tea leaves;YOLOv8m algorithm

期刊名称： Plant Physiology and Biochemistry

ISSN： 0981-9428

年卷期： 2024 年 212 卷

页码：

收录情况： SCIE（2024版）

摘要： The primary challenges in tea production under multiple stress exposures have negatively affected its global market sustainability, so introducing an infield fast technique for monitoring tea leaves' stresses has tremendous urgent needs. Therefore, this study aimed to propose an efficient method for the detection of stress symptoms based on a portable smartphone with deep learning models. Firstly, a database containing over 10,000 images of tea garden canopies in complex natural scenes was developed, which included healthy (no stress) and three types of stress (tea anthracnose (TA), tea blister blight (TB) and sunburn (SB)). Then, YOLOv5m and YOLOv8m algorithms were adapted to discriminate the four types of stress symptoms; where the YOLOv8m algorithm achieved better performance in the identification of healthy leaves (98%), TA (92.0%), TB (68.4%) and SB (75.5%). Furthermore, the YOLOv8m algorithm was used to construct a model for differentiation of disease severity of TA, and a satisfactory result was obtained with the accuracy of mild, moderate, and severe TA infections were 94%, 96%, and 91%, respectively. Besides, we found that CNN kernels of YOLOv8m could efficiently extract the texture characteristics of the images at layer 2, and these characteristics can clearly distinguish different types of stress symptoms. This makes great contributions to the YOLOv8m model to achieve high-precision differentiation of four types of stress symptoms. In conclusion, our study provided an effective system to achieve low-cost, high-precision, fast, and infield diagnosis of tea stress symptoms in complex natural scenes based on smartphone and deep learning algorithms.

分类号：

  • 相关文献

[1]Establishment of The Crop Growth and Nitrogen Nutrition State Model Using Spectral Parameters Canopy Cover. Tao Zhi-qiang,Bagum, Shamim Ara,Ma Wei,Zhou Bao-yuan,Fu Jin-dong,Cui Ri-xian,Sun Xue-fang,Zhao Ming. 2016

[2]Optimization Of Preliminary Purification Conditions F.or Protein Extraction From T ea Residues. Ni, X. H.,Zeng, L.,Li, X. H.,Tu, Z.,Cui, Q. Y.,Chen, X.,Sun, K.,Li, J.. 2018

[3]Measurement of Chlorophyll Content and Distribution in Tea Plant's Leaf Using Hyperspectral Imaging Technique. Chen Quan-sheng,Zhao Jie-wen,Wang Kai-liang,Ouyang Qin. 2011

[4]Optimization of a tannase-assisted process for obtaining teas rich in theaflavins from Camelia sinensis leaves. Shuang Liang,Fang Wang,Jianxin Chen,Daniel Granato,Lijun Li,Jun Feng Yin,Yong Quan Xu. 2022

[5]Recent advances in chemical characterization, emerging applications, and biological activities of tea polysaccharides and their conjugates from leaves and flowers: A review. Ahmed K. Rashwan,Riham A. El-Shiekh,Abdelkader Bassiony,Asem M. Abdelshafy,Ahmed I. Osman,Hala A. Younis,Fanrui Zhou,Youssuf A. Gherbawy,Hesham R. El-Seedi,Jiang Shi,Wei Chen. 2025

作者其他论文 更多>>