Skin Disease Detection And Classification Using Cnn

<<<<<<< HEAD # Skin Disease Prediction AI This project is a Deep Learning application designed to classify various skin diseases from images. It uses a Convolutional Neural Network (CNN) built with **TensorFlow/Keras** and provides a user-friendly **Flask** web interface for real-time predictions. ## 🚀 Features - **High-Accuracy Classification**: Trained on a diverse dataset of skin conditions. - **Web Interface**: Modern, responsive web app for easy image upload and analysis. - **Real-Time Inference**: Fast predictions with confidence scores. - **CLI Support**: Command-line scripts for batch processing or quick checks. ## 🛠️ Prerequisites Ensure you have **Python 3.8+** installed. You will need the following libraries: - TensorFlow - Flask - NumPy - Matplotlib (for training visualization) ## 📦 Installation 1. **Clone or Download** this repository to your local machine. 2. **Install Dependencies**: Open your terminal or command prompt in the project directory and run: ```bash pip install tensorflow flask numpy matplotlib ``` ## 📂 Project Structure ``` skin project/ ├── data set/ # Dataset directory (Test/Train split) ├── static/ # CSS and JavaScript for the web app │ ├── style.css │ └── script.js ├── templates/ # HTML templates │ └── index.html ├── app.py # Flask Web Application entry point ├── train_model.py # Script to train the CNN model ├── evaluate_model.py # Script to evaluate model performance ├── predict.py # CLI script for single image prediction ├── skin_disease_model.keras # Saved trained model file └── README.md # Project documentation ``` ## 🖥️ usage ### 1. Running the Web Application (Recommended) This starts the local web server where you can upload images via a graphical interface. 1. Run the Flask app: ```bash python app.py ``` 2. Wait for the message: `Model loaded successfully`. 3. Open your web browser and go to: ``` http://127.0.0.1:5000 ``` 4. Drag and drop an image or click to upload, then click **"Analyze Image"**. ### 2. Training the Model If you want to retrain the model with new data: 1. Ensure your data is organized in `data set/train` and `data set/test` with subfolders for each class. 2. Run: ```bash python train_model.py ``` This will save the new model as `skin_disease_model.keras`. ### 3. Evaluating the Model To check the accuracy and loss on the test dataset: ```bash python evaluate_model.py ``` ### 4. Command Line Prediction To predict a single image without starting the web server: 1. Open `predict.py` and modify the image path at the bottom. 2. Run: ```bash python predict.py ``` ## ⚠️ Note - The model expects images to be resized to **180x180** pixels (handled automatically by the scripts). - Ensure the `data set` folder exists if you plan to retrain or if the app needs to load class names dynamically. ## 🤝 Contributing Feel free to fork this project and submit pull requests for improvements! ======= # Skin-disease-detection-and-classification-using-cnn https://github.com/varshitha-g/Skin-Disease-Prediction >>>>>>> b967eb6c0c349a02ab1be9e38ecf9c4c469235c6 update README