Spaces:
Sleeping
Sleeping
| license: apache-2.0 | |
| title: Heatmap | |
| sdk: streamlit | |
| colorFrom: gray | |
| colorTo: gray | |
| pinned: true | |
| sdk_version: 1.43.2 | |
| app_file: streamlit_app.py | |
| # Deepfake Detection System with Heatmap Visualization | |
| This project implements a deepfake detection system that processes images through multiple stages: | |
| 1. **Verification Module**: Uses Nvidia AI model for image comparison | |
| - Calculates SMI (Structural Matching Index) | |
| - Generates difference images | |
| - | |
| Applies threshold visualization | |
| - Adds bounding boxes around detected areas | |
| 2. **Labeling System**: Labels detected areas based on threat level | |
| 3. **Heatmap Visualization**: Creates heatmaps highlighting high-threat areas | |
| ## Project Structure | |
| - `deepfake_detector.py`: Core detection functionality using Nvidia AI model | |
| - `image_processor.py`: Image processing utilities | |
| - `labeling.py`: Threat labeling system | |
| - `heatmap_generator.py`: Heatmap visualization tools | |
| - `main.py`: Main application entry point | |
| - `requirements.txt`: Project dependencies | |
| ## Setup and Installation | |
| ```bash | |
| pip install -r requirements.txt | |
| ``` | |
| ## Usage | |
| ```bash | |
| python main.py --input_dir /path/to/images --output_dir /path/to/output | |
| ``` |