Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Apr 13;13(1):6078.
doi: 10.1038/s41598-023-33270-4.

Tea leaf disease detection and identification based on YOLOv7 (YOLO-T)

Md Janibul Alam Soeb #  1 , Md Fahad Jubayer #  2 , Tahmina Akanjee Tarin  3 , Muhammad Rashed Al Mamun  3 , Fahim Mahafuz Ruhad  4 , Aney Parven  5   6 , Nabisab Mujawar Mubarak  7 , Soni Lanka Karri  8 , Islam Md Meftaul  9   10
Affiliations

Tea leaf disease detection and identification based on YOLOv7 (YOLO-T)

Md Janibul Alam Soeb et al. Sci Rep. .

Abstract

A reliable and accurate diagnosis and identification system is required to prevent and manage tea leaf diseases. Tea leaf diseases are detected manually, increasing time and affecting yield quality and productivity. This study aims to present an artificial intelligence-based solution to the problem of tea leaf disease detection by training the fastest single-stage object detection model, YOLOv7, on the diseased tea leaf dataset collected from four prominent tea gardens in Bangladesh. 4000 digital images of five types of leaf diseases are collected from these tea gardens, generating a manually annotated, data-augmented leaf disease image dataset. This study incorporates data augmentation approaches to solve the issue of insufficient sample sizes. The detection and identification results for the YOLOv7 approach are validated by prominent statistical metrics like detection accuracy, precision, recall, mAP value, and F1-score, which resulted in 97.3%, 96.7%, 96.4%, 98.2%, and 0.965, respectively. Experimental results demonstrate that YOLOv7 for tea leaf diseases in natural scene images is superior to existing target detection and identification networks, including CNN, Deep CNN, DNN, AX-Retina Net, improved DCNN, YOLOv5, and Multi-objective image segmentation. Hence, this study is expected to minimize the workload of entomologists and aid in the rapid identification and detection of tea leaf diseases, thus minimizing economic losses.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
Research data collection places; (A) National Tea Company Ltd., (B) Malnicherra Tea Garden, (C) Nur Jahan Tea Garden, (D) Finlay Tea Estate.
Figure 2
Figure 2
The geographical locations of four tea gardens studied in this research in Sylhet, Bangladesh.
Figure 3
Figure 3
Images of tea leaf diseases: (a) red spider, (b) tea mosquito bug, (c) black rot, (d) brown blight, (e) leaf rust.
Figure 4
Figure 4
Block diagram of training and testing the proposed YOLOv7 model.
Figure 5
Figure 5
Network architecture diagram of YOLOv7. The whole architecture contains 4 general modules, namely, an input terminal, backbone, head, and prediction, along with 5 basic components: CBS, MP, ELAN, ELAN-H.
Figure 6
Figure 6
Labels and label distribution, (a) number and class of labels in the dataset, (b) location of the labels in the images of the dataset and the size of the labels in the dataset, (c) ground truth box.
Figure 7
Figure 7
Visual analysis of model evaluation indicators (Precision, recall, and mAP@0.5 for the proposed YOLOv7) during training.
Figure 8
Figure 8
Operation results curve; (a) precision-recall curve, (b) precision-confidence curve, (c) F1-confidence curve, and (d) recall-confidence curve.
Figure 9
Figure 9
Confusion matrix diagram for the proposed YOLO-T model.
Figure 10
Figure 10
Some examples of tea leaf disease detection results using YOLOv7. The bounding boxes consist the images of diseased tea leaves.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Sanlier N, Gokcen BB, Altuğ M. Tea consumption and disease correlations. Trends Food Sci. Technol. 2018;78:95–106. doi: 10.1016/j.tifs.2018.05.026. - DOI
    1. Verma HV. Coffee and tea: Socio-cultural meaning, context and branding. Asia-Pac. J. Manag. Res. Innov. 2013;9(2):157–170. doi: 10.1177/2319510X13504283. - DOI
    1. Debnath B, Haldar D, Purkait MK. Potential and sustainable utilization of tea waste: A review on present status and future trends. J. Environ. Chem. Eng. 2021;9(5):106179. doi: 10.1016/j.jece.2021.106179. - DOI
    1. Hu G, Yang X, Zhang Y, Wan M. Identification of tea leaf diseases by using an improved deep convolutional neural network. Sustain. Comput. Inf. Syst. 2019;24:100353. doi: 10.1016/j.suscom.2019.100353. - DOI
    1. Ahmed JU, Mozahid M, Dhar AR, Alamgir M, Jannat A, Islam M. Food security and dietary diversity of tea workers of two tea gardens in greater Sylhet district of Bangladesh. GeoJournal. 2021;86(2):1015–1027. doi: 10.1007/s10708-019-10108-z. - DOI

Publication types