A virtual calculator powered by OpenCV, MediaPipe, and Generative AI, enabling users to solve complex math problems by drawing equations on-screen using hand gestures. The system captures the visual input, processes it via Google's Gemini LLM API key, and displays a detailed solution in real time.
python,OpenCV,LLM,Flask,Html,CSS,JavaScript
#System Architechture
To use the AI features, you need a Gemini API key. You can create a key with one click in Google AI Studio. Replace YOUR_API_KEY in app.py with your own API Key. Ensure you have the latest version of Python installed on your system. Quickly clone the repository and change the working directory.
git clone https://github.com/codewithsanaa/Vision-based-Math-Solver-using-OpenCv-and-Generative-AI.git cd Vision-based-Math-Solver-using-OpenCv-and-Generative-AI/
We have to install all the dependencies of the project. Optionally, you can create a Python virtual environment. Run the following commands in your terminal: python -m venv venv pip install -r requirements.txt
Now we can run the flask server with python app.py command.