This project merges image capturing with AI-driven content analysis to form an interactive application. Utilizing Python and Tkinter for the graphical interface, it employs OpenCV for image capture and Google's AI for sophisticated content analysis. This setup offers a practical exploration of AI's capabilities in real-time image processing.
You can check the link of the documentation here
- Real-time image capturing from a webcam.
- AI-powered content description using Google's API.
- Python 3.x
- OpenCV
- Pillow
- python-dotenv
- Google GenerativeAI library
- Clone the repository:
git clone [repository-url] - Install required packages:
pip install -r requirements.txt
Run main.py to start the application:
python main.py
main.py: Main application script.video_stream.py: Handles the video streaming.content_description.py: Manages AI-based content description.
- Create a
.envfile with your Google API key:GOOGLE_API_KEY=your_api_key_here
Specify your license or state that the project is open-source.
Instructions on how to contribute to the project.
Email: hamzah.m.jomaa@gmail.comLinkedIn: hamzajomaa
For more information, check out my Medium profile.