https://github.com/sayedgamal99/plant-disease-classifier

https://github.com/sayedgamal99/plant-disease-classifier

Last synced: 8 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/sayedgamal99/plant-disease-classifier
• Owner: sayedgamal99
• Created: 2024-12-21T16:08:49.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2025-03-08T21:56:46.000Z (over 1 year ago)
• Last Synced: 2025-03-08T22:26:42.878Z (over 1 year ago)
• Language: Python
• Size: 4.79 MB
• Stars: 0
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# 🌿 Plant Disease Classifier



  





  

  

  

  





  A deep learning-based web application that diagnoses diseases in plant leaves using convolutional neural networks (CNNs).



![Plant Disease Classifier Demo](https://your-repo-url/images/demo.gif)

## 🚀 Live Demo

The application is currently deployed and available at:

[https://plant-disease-classifier-cnn.streamlit.app/](https://plant-disease-classifier-cnn.streamlit.app/)

## Video Demonstration



  



## ✨ Features

- **Instant Disease Detection**: Upload an image of a plant leaf and get immediate diagnosis results

- **Comprehensive Diagnosis**: Provides detailed information on detected diseases, including causes, treatments, and prevention

- **User-Friendly Interface**: Clean, intuitive UI with image previews and visualization of results

- **Multiple Plant Support**: Currently supports tomatoes, potatoes, and bell peppers

- **High Accuracy**: 96.5% accuracy on test datasets

- **Example Images**: Try the application with pre-loaded example images

## 🧪 Supported Plant Diseases

The model can currently identify the following plants and diseases:

- **Tomato**:

  - Healthy

  - Bacterial Spot

  - Early Blight

  - Late Blight

  - Leaf Mold

  - Septoria Leaf Spot

  - Spider Mites

  - Target Spot

  - Yellow Leaf Curl Virus

  - Mosaic Virus

- **Potato**:

  - Healthy

  - Early Blight

  - Late Blight

- **Bell Pepper**:

  - Healthy

  - Bacterial Spot

## 🔧 Model Architecture

The application uses a custom CNN architecture with the following components:

- 5 convolutional blocks with batch normalization and ReLU activation

- Global Average Pooling

- Fully connected layers with dropout for regularization

- Trained on the PlantVillage dataset with data augmentation techniques

- Achieves 96.5% accuracy on the test set