Skip to content

Deep Learning CNN Model for Tomato Leaf Disease Prediction #260

Description

@keshripritesh

🌱 New Project: Deep Learning CNN Model for Tomato Leaf Disease Prediction

📌 Description

This project introduces a Deep Learning-based Convolutional Neural Network (CNN) model trained on a Tomato Leaf Image Dataset to detect and classify various tomato plant diseases. The model can distinguish between multiple disease categories as well as healthy leaves, helping farmers and researchers in early disease detection and crop protection.


🦠 Diseases Covered

The trained CNN model can accurately classify tomato leaves into the following categories:

  • Bacterial spot
  • Early blight
  • Late blight
  • Leaf mold
  • Septoria leaf spot
  • Spider mites (Two-spotted spider mite)
  • Target spot
  • Tomato Yellow Leaf Curl Virus
  • Healthy Tomato Leaf 🌿

📊 Model Performance

  • ✅ Training Accuracy: 99.96%
  • ✅ Testing Accuracy: 96.99%
  • ⚖️ The model is not overfit or underfit, indicating strong generalization.

🖼️ Sample Outputs

  • Healthy Tomato Leaf
Image
  • Tomato Leaf with Bacterial Spot
Image
  • Tomato Leaf with Septoria Leaf Spot
Image
  • Tomato Leaf with Tomato Yellow Leaf Curl Virus
Image

📂 Repo Placement

projects/Day-XXX-Tomato-Disease-Prediction-CNN/
│── dataset/
│── model/
│── tomato_cnn.py
│── README.md

⚙️ Tech Stack

  • Python 3
  • TensorFlow / Keras (Deep Learning)
  • OpenCV / Pillow (Image Preprocessing)
  • NumPy, Pandas (Data Handling)
  • Matplotlib / Seaborn (Visualization)

▶️ How to Run

  1. Clone the repository

  2. Navigate to the project folder

  3. Install dependencies:

    pip install tensorflow keras numpy pandas matplotlib seaborn opencv-python
  4. Train or load the pretrained model:

    python tomato_cnn.py
  5. Test on sample images


🚀 Future Enhancements

  • Deploy as a Streamlit web app for user-friendly predictions
  • Add real-time detection using camera feed
  • Extend the dataset with more crop varieties
  • Provide disease treatment recommendations along with predictions

🔗 Event: GirlScript Summer of Code (GSSoC’25)
🏷️ Type: New Project Addition


Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions