A camera application with OCR and text-to-speech capabilities designed for accessibility.
- Live camera feed with multiple filters and zoom
- OCR text recognition with text-to-speech output
- Real-time text overlay showing detected text
- Customizable controls and settings persistence
- Multiple camera support with format switching
-
Run the install script:
bash install.sh
-
Run the application:
bash run_venv.sh
-
Install system dependencies:
# Ubuntu/Debian sudo apt update && sudo apt install -y python3 python3-pip python3-venv tesseract-ocr tesseract-ocr-eng espeak-ng espeak-ng-data # Fedora sudo dnf install -y python3 python3-pip python3-virtualenv tesseract espeak-ng espeak-ng-devel # Arch Linux sudo pacman -S --needed python python-pip python-virtualenv tesseract tesseract-data-eng espeak-ng
-
Create virtual environment:
python3 -m venv venv source venv/bin/activate -
Install Python packages:
pip install -r requirements.txt
-
Run the application:
python3 src/camera_app.py # Or use the convenience scripts: bash run_venv.sh # (with virtual environment) bash run.sh # (system Python)
- O - OCR read text (one-time)
- L - Toggle live OCR overlay
- Space - Freeze/unfreeze frame
- \ - Cycle zoom levels
- Arrow keys - Pan when zoomed
- [/] - Change filters
- ;/' - Adjust filter strength
- F - Toggle fullscreen
- ` - Show/hide help overlay
SightBridge/
├── run.sh # Main launcher (with venv)
├── src/ # Application source
│ ├── camera_app.py # Main application
│ ├── keybindings.json # Key bindings config
│ └── camera_settings.json # Camera settings
├── tools/ # Development tools
│ └── ocr_testing/ # OCR testing utilities
└── requirements.txt # Python dependencies
See tools/ocr_testing/README.md for OCR debugging tools.