Hand Gesture Recognition is a significant area of research in Human-Computer Interaction (HCI) technology. This project demonstrates the development of a real-time Hand Gesture Recognizer using the MediaPipe framework, TensorFlow, and OpenCV in Python.
- Introduction
- Prerequisites
- Installation
- Running the Python script
- Running the Flask Web Application
- Accessing the Application
- Contributing Guidelines
- License
Gesture recognition plays a crucial role in various applications such as virtual environment control, sign language translation, robot control, and music creation. This project utilizes MediaPipe, an open-source framework developed by Google, for hand detection and keypoint estimation. TensorFlow is employed for building and deploying a pre-trained gesture recognition model. OpenCV facilitates real-time image processing and webcam interaction.
Before running the project, ensure you have the following installed:
- Python 3.x
- OpenCV 4.5
- MediaPipe 0.8.11
- TensorFlow 2.5.0
- NumPy 1.19.3
Create a new virtual environment with Python version 3 or higher installed. You can install the required packages using pip:
pip install -r requirements.txt
This ensures that you have a clean environment with the necessary dependencies installed to run the project.
- Clone this repository to your local machine and go to the project directory.
git clone https://github.com/KelvinPuyam/Hand-Gesture-Recognition.git
cd Hand-Gesture-Recognition
- Install the prerequisites as mentioned above.
pip install -r requirements.txt
- Run the Python script.
python hand_gesture_detection.py
- Ensure your webcam is connected and functional.
- Perform hand gestures in front of the webcam to observe real-time recognition.
After cloning the repository and navigating to the project directory, ensure you have installed the required dependencies.
Run the Flask web application using the following command:
python app.py
When you run app.py
, the Flask web application initializes the hand gesture detection system using MediaPipe, TensorFlow, and OpenCV. It starts a server listening on http://127.0.0.1:5000.
Ensure your webcam is connected and functional.
Open a web browser and go to http://127.0.0.1:5000.
Upon accessing the provided URL, the web application interface for hand gesture detection will be displayed. You can perform hand gestures in front of the webcam to observe real-time recognition.
Contributions are welcome! Feel free to open issues or submit pull requests to improve this project.
This project is licensed under the MIT License.