Update README.md
Browse files
README.md
CHANGED
|
@@ -1,10 +1,75 @@
|
|
| 1 |
---
|
| 2 |
-
title:
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
-
colorTo:
|
| 6 |
-
sdk:
|
|
|
|
|
|
|
| 7 |
pinned: false
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
title: Smart Waste Classification
|
| 3 |
+
emoji: ♻️
|
| 4 |
+
colorFrom: green
|
| 5 |
+
colorTo: blue
|
| 6 |
+
sdk: gradio
|
| 7 |
+
sdk_version: 4.7.1
|
| 8 |
+
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
+
license: mit
|
| 11 |
---
|
| 12 |
|
| 13 |
+
# ♻️ Smart Waste Classification
|
| 14 |
+
|
| 15 |
+
An AI-powered web application that classifies different types of waste materials to help with proper recycling and disposal.
|
| 16 |
+
|
| 17 |
+
## Features
|
| 18 |
+
|
| 19 |
+
- **Image Classification**: Upload images of waste items for automatic classification
|
| 20 |
+
- **10 Categories**: Supports classification of biological waste, glass (brown/green/white), cardboard, metal, paper, plastic, shoes, and general trash
|
| 21 |
+
- **Recycling Guidance**: Provides clear guidance on whether items are recyclable or not
|
| 22 |
+
- **Statistics Dashboard**: Track classification statistics with visual charts
|
| 23 |
+
- **Export Reports**: Download classification data as CSV or PDF reports
|
| 24 |
+
|
| 25 |
+
## Supported Waste Categories
|
| 26 |
+
|
| 27 |
+
### Recyclable ♻️
|
| 28 |
+
- Brown Glass
|
| 29 |
+
- Green Glass
|
| 30 |
+
- White Glass
|
| 31 |
+
- Metal
|
| 32 |
+
- Plastic
|
| 33 |
+
- Paper
|
| 34 |
+
- Cardboard
|
| 35 |
+
|
| 36 |
+
### Non-Recyclable 🗑️
|
| 37 |
+
- Biological Waste
|
| 38 |
+
- Shoes
|
| 39 |
+
- General Trash
|
| 40 |
+
|
| 41 |
+
## How to Use
|
| 42 |
+
|
| 43 |
+
1. **Upload Image**: Click "Choose File" and select an image of waste material
|
| 44 |
+
2. **Classify**: Click "Classify Waste" to get AI prediction
|
| 45 |
+
3. **View Result**: See the predicted category, confidence score, and recycling guidance
|
| 46 |
+
4. **Check Stats**: Visit the statistics page to see classification trends
|
| 47 |
+
5. **Export Data**: Download your classification history as CSV or PDF
|
| 48 |
+
|
| 49 |
+
## Technology Stack
|
| 50 |
+
|
| 51 |
+
- **Backend**: Flask (Python web framework)
|
| 52 |
+
- **AI Model**: EfficientNet-B0 trained on waste classification dataset
|
| 53 |
+
- **Frontend**: Bootstrap 5 for responsive UI
|
| 54 |
+
- **Data Visualization**: Matplotlib for statistics charts
|
| 55 |
+
- **Export**: CSV and PDF report generation
|
| 56 |
+
|
| 57 |
+
## Model Information
|
| 58 |
+
|
| 59 |
+
The application uses a fine-tuned EfficientNet-B0 model trained specifically for waste classification. The model achieves high accuracy across all supported categories and provides confidence scores for each prediction.
|
| 60 |
+
|
| 61 |
+
## Limitations
|
| 62 |
+
|
| 63 |
+
- Camera functionality is not available in Hugging Face Spaces
|
| 64 |
+
- Maximum file size limits may apply
|
| 65 |
+
- Supported image formats: PNG, JPG, JPEG, GIF, BMP
|
| 66 |
+
|
| 67 |
+
## License
|
| 68 |
+
|
| 69 |
+
This project is licensed under the MIT License.
|
| 70 |
+
|
| 71 |
+
## Acknowledgments
|
| 72 |
+
|
| 73 |
+
- Built with TensorFlow/Keras
|
| 74 |
+
- UI components from Bootstrap
|
| 75 |
+
- Background images from Unsplash
|