Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A curated dataset and lightweight deep learning framework for tea leaf disease classification.

Sakibul Hasan Chowdhury1, Md Shohel Arman1, Masrafe Bin Hannan Siam1

  • 1Data Science Lab, Department of Software Engineering, Daffodil International University, Daffodil Smart City, Birulia, Dhaka, Bangladesh.

Plos One
|May 15, 2026
PubMed
Summary

Related Concept Videos

Light Acquisition02:16

Light Acquisition

In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
Classification of Illness01:17

Classification of Illness

The meaning of illness is individualized to each person who experiences an alteration in health. In contrast, disease is a medical term indicating a pathological change in the structure and function of the body or mind. It is a condition that has specific symptoms and boundaries.
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe and...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Effects of similarity networks in graph-based multi-omics classification.

PloS one·2026
See all related articles

A new hybrid deep learning model accurately detects tea plant diseases like Blight and Red Rust. This approach enhances crop yield and quality by enabling early, reliable disease identification in precision agriculture.

Area of Science:

  • Agricultural Science
  • Computer Science
  • Plant Pathology

Background:

  • Tea cultivation is economically vital but threatened by diseases like Blight, Red Rust, and Helopeltis.
  • Manual inspection for tea plant diseases is slow, subjective, and prone to errors, hindering timely intervention.
  • Existing deep learning models struggle to simultaneously analyze fine-grained disease symptoms and overall plant health.

Purpose of the Study:

  • To develop a novel deep learning architecture for accurate and efficient detection of major tea plant diseases.
  • To improve early disease identification for enhanced tea crop yield and quality management.
  • To create a computationally balanced model suitable for real-time monitoring on Internet of Things (IoT) edge devices.

Main Methods:

Related Experiment Videos

  • A Hybrid Feature Fusion architecture was proposed, combining EfficientNetV2-Small for local texture analysis and MobileNetV3-Small for global context.
  • The model was trained and validated on a dataset of 2,000 annotated tea leaf images across four classes (Blight, Red Rust, Helopeltis, Healthy).
  • Standardized preprocessing and dynamic data augmentation techniques were employed to enhance model robustness and generalization.

    • Main Results:

    • The hybrid model achieved a peak classification accuracy of 96.80% and a macro Area Under the Curve (AUC) of 0.9980.
    • It demonstrated superior precision-recall balance and convergence stability compared to single-branch architectures like Vision Transformer and ResNet50.
    • While EfficientNetV2-B3 showed slightly higher raw accuracy, the proposed framework offers better overall performance and suitability for edge deployment.

    Conclusions:

    • The Hybrid Feature Fusion deep learning model offers a highly reliable and computationally efficient solution for real-time tea plant disease monitoring.
    • This methodology significantly advances precision agriculture by enabling rapid and accurate identification of critical crop diseases.
    • The model's balanced performance makes it ideal for integration into IoT edge devices for on-site disease detection and management.