High-resolution dataset for tea garden disease management: Precision agriculture insights

  • 0Department of Computer Science and Engineering, Daffodil International University, Dhaka, Bangladesh.

|

|

Summary

This summary is machine-generated.

This study introduces a high-resolution image dataset for tea garden disease detection. It aids in developing precision agriculture tools for early disease identification and management, boosting tea production sustainability.

Area Of Science

  • Agricultural Science
  • Plant Pathology
  • Computer Vision

Background

  • Tea plantations are vital for economic development but face significant losses due to plant diseases.
  • Existing methods for disease management lack precision, impacting tea quality and yield.
  • Advanced digital tools are needed for effective tea garden disease monitoring.

Purpose Of The Study

  • To present a comprehensive, high-resolution image dataset for tea garden disease management.
  • To facilitate the development of automated systems for early disease detection and classification.
  • To support precision agriculture techniques in tea cultivation.

Main Methods

  • Collected a dataset of 3960 high-resolution (1024x1024 pixels) JPG images of tea leaves using smartphones.
  • Images captured include common diseases like Tea Leaf Blight, Tea Red Leaf Spot, and Tea Red Scab, alongside healthy leaves.
  • Dataset includes environmental statistics and plant health indicators.

Main Results

  • A rich, diverse dataset suitable for training machine learning models for disease identification.
  • Provides a benchmark for developing and evaluating automated tea plant disease detection algorithms.
  • Enables detailed analysis of disease prevalence and correlation with environmental factors.

Conclusions

  • The dataset is a valuable resource for advancing precision agriculture in tea cultivation.
  • It enables the creation of smart farming tools for automated disease tracking and targeted interventions.
  • Facilitates enhanced sustainability and efficiency in tea production through data-driven insights.