Applying Convolutional Neural Networks for Early Detection of Diseases in Sesame Leaf

The Sesame Leaf Disease Dataset consists of 3,540 high-quality images, collected from sesame cultivation fields in Pabna District, Bangladesh. Images were captured under natural field conditions using high-resolution smartphone cameras to ensure clarity of disease symptoms. The dataset is organized into four major classes of sesame leaves.

Data Collection Details:
Captured Using:
1. Realme 8 (64 MP, f/1.79 aperture)
2. Redmi Note 12 Pro (50MP, f/1.79 aperture)

Data Source Location:
1. Pabna District, Bangladesh (Latitude: 24.006355, Longitude: 89.237202)

Number of Images (Original 3,540):

1. Healthy: 1,120
2. Insect Damage: 880
3. Leaf Spot: 790
4. Powdery Mildew: 750

Sesame Leaf Dataset Distribution

1. Healthy Leaf – Original Images: 1,335, Augmented Images: 3,000
2. Leaf Spot Disease – Original Images: 587, Augmented Images: 3,000
3. Yellowing Leaf Syndrome – Original Images: 894, Augmented Images: 3,000
4. Insect Leaf Damage – Original Images: 724, Augmented Images: 3,000
Total: Original = 3,540, Augmented = 12,000

Key Applications of the Sesame Leaf Disease Dataset

Early Disease Detection: Leaf images help train AI models to detect sesame diseases at an early stage, reducing crop loss.
Precision Agriculture: Farmers can use mobile or IoT-based apps powered by trained models to get instant disease diagnosis in the field.
Decision Support Systems: Assists agricultural experts and policymakers in monitoring disease spread and planning effective management strategies.
Smart Farming Tools: Can be integrated into drones and smart cameras for large-scale sesame field surveillance.
Educational and Research Use: Acts as a benchmark dataset for computer vision, deep learning, and plant pathology research.
Model Benchmarking: Useful for testing and comparing performance of different CNN architectures and transfer learning models.
Scalable to Other Crops: The methodology can be extended to detect diseases in other plants, ensuring wider applications in agriculture.