Related Experiment Video
Updated: Sep 12, 2025
03:31
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
Published on: December 15, 2023
636
Ensemble-based sesame disease detection and classification using deep convolutional neural networks (CNN)
Abenet Alazar Hailu1, Banchalem Chebudie Kassa2, Esubalew Asmare Desta2
1Department of Information Technology, College of Informatics, and University of Gondar, Gondar, Ethiopia. abenet365@gmail.com.
Scientific Reports
|August 6, 2025
Summary
This study developed an ensemble deep learning model using convolutional neural networks (CNNs) to accurately detect and classify sesame diseases like phyllody and bacterial blight, achieving 96.83% accuracy for precision agriculture.
Area of Science:
- Agricultural Science
- Computer Science
- Plant Pathology
Background:
- Sesame cultivation faces significant yield and quality losses due to diseases such as phyllody and bacterial blight.
- Accurate and early disease detection is crucial for effective management and maintaining crop productivity.
Purpose of the Study:
- To develop and evaluate an ensemble-based deep learning model for the detection and classification of sesame leaf diseases.
- To leverage multiple Convolutional Neural Network (CNN) architectures for enhanced diagnostic accuracy.
Main Methods:
- An ensemble model was constructed by integrating three CNN architectures: ResNet-50, DenseNet-121, and Xception.
- The models were trained and validated on a comprehensive dataset of sesame leaf images representing healthy and diseased (phyllody, bacterial blight) states.
Main Results:
- The ensemble model achieved a high overall accuracy of 96.83% in classifying sesame leaf conditions.
- The combined approach demonstrated superior performance and robustness compared to individual models.
Conclusions:
- Ensemble deep learning models offer a powerful and accurate tool for identifying sesame diseases.
- This approach has significant implications for precision agriculture, enabling timely interventions and supporting sustainable sesame production.
