Related Concept Videos
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
Sort by
Same author
A minimal-net CNN model for an IoT-based brain tumor detection and monitoring system.
Scientific reports·2026
Same author
A novel qVGG-4 model for optimizing a parameterized quantum circuit in a quantum-IoT-based brain tumor detection and monitoring system.
Computer methods and programs in biomedicine·2026
Multi-format open-source sweet orange leaf dataset for disease detection, classification, and analysis.
Yousuf Rayhan Emon1, Md Taimur Ahad1, Golam Rabbany1
1Daffodil International University, Daffodil Smart City (DSC), Birulia, Savar, Dhaka 1216, Bangladesh.
Data in Brief
|August 5, 2024
Summary
A new dataset of sweet orange diseases in Bangladesh was created to improve fruit production. This machine learning dataset aids in early disease detection and classification, benefiting farmers and agri-engineering research.
Area of Science:
- Agricultural Science
- Computer Vision
- Machine Learning
Background:
- Sweet orange cultivation is economically important in Bangladesh, but disease outbreaks significantly reduce fruit yield.
- Existing machine learning (ML) datasets for fruit disease diagnosis are insufficient, particularly for region-specific variations like those found in Bangladesh.
- Computer-aided diagnosis using ML models offers a promising solution for accurate and timely detection of sweet orange diseases.
Purpose of the Study:
- To develop a comprehensive, high-quality dataset of sweet orange plant diseases specific to Bangladesh.
- To facilitate the application of machine learning and computer vision techniques for disease identification and classification in sweet oranges.
- To support advancements in agricultural engineering and provide tools for farmers to mitigate crop losses.
Main Methods:
- Collected a dataset of high-resolution images of sweet orange plants in August.
- The dataset includes various disease conditions such as Citrus Canker, Citrus Greening, Die Back, Powdery Mildew, Yellow Leaves, and healthy samples.
- Ensured the dataset format is suitable for diverse machine learning algorithm requirements.
Main Results:
- A novel dataset of sweet orange diseases from Bangladesh has been successfully compiled.
- The dataset captures multiple disease types and healthy leaf images, crucial for training diagnostic models.
- Provides a valuable resource for researchers and developers in the field of agricultural machine learning.
Conclusions:
- The developed dataset addresses the limitations of existing resources for sweet orange disease diagnosis in Bangladesh.
- It enables the development and validation of advanced ML models for early disease detection, potentially improving crop yields.
- This resource can assist farmers in implementing timely preventive measures, thereby reducing economic losses and supporting sustainable sweet orange farming.