The Augmented Reality Assistant is a virtual assistant inspired by JARVIS from Iron Man. Developed using Python, OpenCV, Google's Generative AI (Gemini), and Tesseract OCR, this project provides a real-time, interactive assistant with a range of functionalities.
JARVIS.-.The.Augmented.Reality.Assistant.mp4
| Feature | Project.py | server.py |
|---|---|---|
| Virtual Assistant | ✅ | ✅ |
| Real-Time Information | ✅ | ✅ |
| Text Detection | ✅ | ✅ |
| Hand Gesture Interaction | ✅ | ✅ |
| Sound Effects | ✅ | ✅ |
| Face Detection | ✅ | ❌ |
| Google Maps Integration | ✅ | ❌ |
| Temperature | ✅ | ✅ |
| Location | ✅ | ✅ |
| Coordinates | ✅ | ✅ |
| Time | ✅ | ✅ |
| Mic Connection Status | ✅ | ✅ |
| Internet Connection Status | ✅ | ✅ |
| Access Through Multiple Devices | ❌ | ✅ |
- Python: For the backend logic and server-side scripting.
- OpenCV: For computer vision tasks.
- Google Generative AI (Gemini): For generating responses and explanations.
- Tesseract OCR: For optical character recognition to detect text from images.
- Requests: For making HTTP requests to APIs.
- pyttsx3: For text-to-speech conversion.
- SpeechRecognition: For speech-to-text conversion.
- Flask: For hosting the project on HTTP (server.py).
- Python
- Tesseract OCR (Install Tesseract-OCR and add it to your system's PATH)
- Google Generative AI API Key (Gemini API key)
- OpenWeatherMap API Key (For weather data)
-
Clone the repository:
git clone https://github.com/TejasShirsath/Augmented_Reality_Assistant.git cd Augmented_Reality_Assistant -
Install requirements:
pip install -r requirements.txt
-
Configure environment variables:
Create a
.envfile in the project root directory and add the following variables:GENAI_API_KEY=your_google_generative_ai_api_key WEATHER_APP_ID=your_openweathermap_api_key -
Update paths in
Project.py:- Cascade Path: Update the
cascade_pathvariable with the path tohaarcascade_frontalface_default.xml. - Tesseract Path: Update the
tesseract_pathvariable with the path totesseract.exe.
- Cascade Path: Update the
-
Run the project:
For desktop application (Project.py):
python Project.py
For web-based application (server.py):
python server.py
AR assistant have the potential to greatly enhance our daily lives, providing us with relevant information and helping us perform tasks more efficiently. The future of AR technology is bright, with continued advancements in AI and computer vision expected to drive the growth of AR assistants. As AR technology continues to evolve, it will play an increasingly important role in shaping the future of how we interact with the digital world.
This project is licensed under the MIT License - see the LICENSE file for details.