EcoSort is an AI-powered application designed to automate the classification of waste materials. Built with Streamlit and TensorFlow, it leverages a fine-tuned VGG16 Deep Learning model to accurately identify garbage into 12 distinct categories.
This project aims to assist in proper waste segregation, promoting recycling efficiency and environmental sustainability.
- Real-time Classification: Instantly identify waste types from uploaded images.
- Sample Testing: Try the model with built-in sample images (Textile, Plastic, etc.).
- MNC-Themed UI: A professional, clean, and responsive user interface.
- Comprehensive Documentation: In-app methodology detailed explanation of the model and preprocessing.
- 12-Class Support: Covers a wide range of common waste items.
The model can detect the following classes:
- Battery 🔋
- Biological 🥬
- Brown Glass 🟤
- Cardboard 📦
- Clothes 👕
- Green Glass 🟢
- Metal ⚙️
- Paper 📄
- Plastic 🥤
- Shoes 👟
- Trash 🗑️
- White Glass ⚪
- Language: Python
- Framework: Streamlit
- Deep Learning: TensorFlow / Keras (VGG16 Architecture)
- Image Processing: OpenCV (cv2), Pillow (PIL), NumPy
-
Clone the Repository:
git clone https://github.com/vargheesk/Garbage-Classification.git cd Garbage-Classification -
Create a Virtual Environment (Optional but recommended):
python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate
-
Install Dependencies:
pip install -r requirements.txt
Note: Ensure you have
streamlit,tensorflow,numpy,opencv-python, andpillowinstalled.
Run the Streamlit application:
streamlit run streamlit_app.pyThe app will open in your default browser at http://localhost:8501.
- Architecture: VGG16 (Transfer Learning)
- Input Size: 224 x 224 pixels
- Training: Trained on the Garbage Classification Dataset from Kaggle.
- Preprocessing: RGB conversion, resizing, and pixel normalization (1./255).
Developed for Luminar Python Project.
Reduce, Reuse, Recycle! 🌍