Skip to content

Latest commit

 

History

History
35 lines (34 loc) · 3.35 KB

README.md

File metadata and controls

35 lines (34 loc) · 3.35 KB
Raw

Handsign Detection

Welcome to the Handsign Detection project repository! This project aims to facilitate real-time detection of hand signs, particularly those from the American Sign Language (ASL), using machine learning and computer vision techniques. Through the integration of various libraries such as MediaPipe, scikit-learn, and OpenCV, this model enables users to interact with applications and devices using intuitive hand gestures.

Key Features

  • Real-time Detection: Our model offers instantaneous detection of ASL hand signs, providing seamless interaction for users.
  • Very High Accuracy: The model boasts very high accuracy due to comprehensive training on a wide range of datasets.
  • Comprehensive Training: Trained using MediaPipe for hand tracking, scikit-learn for machine learning with a Random Forest classifier, and OpenCV for image processing, ensuring robust performance across various scenarios.
  • Wide Range of Dataset: The model has been trained on a diverse dataset, enhancing its ability to recognize various hand signs accurately.
  • User-friendly Interface: Extensive documentation and examples are provided for easy integration and usage of the hand sign detection system.
  • Customization Options: Users can customize the model to detect additional ASL hand signs or words, catering to specific communication needs.
  • Meaningful Sentences: In addition to individual hand signs, the model recognizes select words, enabling users to construct meaningful sentences for enhanced communication.

Note: This model supports only the detection of the right hand, as the dataset used for training is specific to right-hand gestures.

Getting Started

  1. Clone the Repository: Clone this repository to your local machine using the following command:
    git clone https://github.com/youutubee/handsign-detection.git
  2. Run the train.py file: After it is successfully run a model.p file will appear in the project directory
  3. Run inference.py: Utilize the provided example scripts to observe the model's performance in real-time.

Contributions

Contributions to this project are highly welcome! Whether you want to optimize the algorithm, expand the vocabulary of recognized hand signs and words, or improve documentation, your contributions are invaluable in advancing this technology.

  1. Fork the repository.
  2. Create a new branch (git checkout -b feature/your-feature).
  3. Make your changes.
  4. Commit your changes (git commit -am 'Add new feature').
  5. Push to the branch (git push origin feature/your-feature).
  6. Create a new Pull Request.

Feedback

Your feedback is essential in refining the Handsign Detection model. Please feel free to report any issues, suggest new features, or provide general feedback to help us improve the system further.