Plant Disease Detection System

Overview

The Plant Disease Detection System is an AI-powered web application built with Streamlit that helps farmers and gardeners identify diseases in tomato and watermelon plants. By simply uploading a photo of a plant leaf, users can receive instant disease diagnosis along with specific treatment recommendations and prevention measures.

Features

• Real-time Disease Detection: Upload leaf images and get immediate analysis
• Multi-crop Support: Currently supports tomatoes (10 classes) and watermelons (4 classes)
• Treatment Recommendations: Provides specific product recommendations and application instructions
• Prevention Tips: Offers guidance on preventing future disease occurrences
• Interactive UI: User-friendly interface with intuitive navigation and visualization
• Visual Analysis: Displays probability distribution of detected diseases

Models

The system utilizes two deep learning models:

Tomato Disease Model

• Architecture: EfficientNetB0 (fine-tuned)
• Classes: 10 classes (9 diseases + healthy)
• Accuracy: ~97% on test set
• Disease Categories:
  • Tomato Mosaic Virus
  • Target Spot
  • Bacterial Spot
  • Tomato Yellow Leaf Curl Virus
  • Late Blight
  • Leaf Mold
  • Early Blight
  • Spider Mites
  • Septoria Leaf Spot
  • Healthy

Watermelon Disease Model

• Architecture: MobileNetV2
• Classes: 4 classes (3 diseases + healthy)
• Accuracy: ~95% on test set
• Disease Categories:
  • Anthracnose
  • Downy Mildew
  • Mosaic Virus
  • Healthy

Installation and Setup

Prerequisites

• Python 3.7+
• TensorFlow 2.x
• OpenCV
• Streamlit
• NumPy
• Matplotlib
• Pillow

Installation Steps

1. Clone the repository:

   git clone https://github.com/yourusername/plant-disease-detection.git
   cd plant-disease-detection

2. Create a virtual environment (optional but recommended):

   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install the required packages:

   pip install -r requirements.txt

4. Download the pre-trained models and place them in the models directory:

   • models/Tomato_EfficientNetB0_finetuned_final.h5
   • models/Watermelon_MobileNetV2_final.h5
   • models/confusion_matrix.png
   • models/Watermelon_MobileNetV2_training_history.png
   • models/Tomato_EfficientNetB0_finetuned_training_history.png
   • models/Head image.jpg

5. Run the application:

   streamlit run app.py

6. Access the application in your web browser at http://localhost:8501

How to Use

1. Navigate to the "Disease Detection" page using the sidebar menu
2. Select the crop type (tomato or watermelon)
3. Upload a clear image of your plant leaf
4. Review the detection results and treatment recommendations

Best Practices for Image Capture

• Take photos in good natural light
• Make sure the leaf is in focus and clearly visible
• Include the entire leaf in the frame
• Avoid shadows or glare on the leaf surface

Treatment Recommendations

The system provides Rallis product recommendations based on the detected disease, including:

• Specific product name and formulation
• Application instructions with dosage and frequency
• Prevention measures to avoid recurrence

Technical Implementation

The application is built using:

• Streamlit: For the web interface
• TensorFlow/Keras: For loading and running the disease detection models
• OpenCV: For image preprocessing
• Matplotlib: For visualization of prediction probabilities
• NumPy: For numerical operations

Future Enhancements

• Add support for additional crops (e.g., cucumbers, peppers)
• Implement multiple disease detection in a single image
• Add severity estimation for detected diseases
• Integrate with weather data for risk prediction
• Add multi-language support

Contact Information

For support, feature requests, or collaboration:

• Developer: Aditya Gupta
• LinkedIn: Aditya Gupta

License

This project is licensed under the MIT License - see the LICENSE file for details.