A comprehensive cotton leaf disease dataset for enhanced detection and classification

Area of Science:

• Agricultural Science
• Computer Science
• Data Science

Background:

• Accurate cotton disease identification is crucial for effective crop management and yield preservation.
• Existing methods often rely on manual inspection, which is time-consuming and prone to errors.
• The development of robust datasets is essential for advancing automated disease detection technologies.

Purpose of the Study:

• To introduce a comprehensive dataset of cotton leaf diseases for agricultural research.
• To enable the development and benchmarking of machine learning models for automated disease detection.
• To support precision agriculture initiatives through improved disease monitoring and management.

Main Methods:

• Field surveys were conducted from October 2023 to January 2024 for meticulous image capture under diverse conditions.
• A dataset comprising 2137 original and 7000 augmented images was created, categorized into eight classes.
• The Inception V3 model was employed to evaluate the dataset's efficacy for disease detection.

Main Results:

• The Inception V3 model achieved a high overall accuracy of 96.03% in classifying cotton leaf diseases.
• The dataset demonstrated significant potential for training deep learning models for automated monitoring.
• The findings highlight the dataset's utility in facilitating timely interventions and targeted treatments.

Conclusions:

• The developed cotton leaf disease dataset is a valuable resource for advancing automated disease detection in agriculture.
• This resource supports precision farming by enabling early diagnosis, reducing chemical use, and improving crop yields.
• The dataset contributes to global efforts in developing disease-resistant cotton varieties and sustainable farming practices.