🧘‍♂️ AI Yoga Trainer – Yoga Pose Recognition and Correction System

A deep learning-based Yoga Trainer that recognizes and corrects Yoga poses in real-time using computer vision and body landmark detection frameworks like MediaPipe.

🌟 Features

• 🎯 Yoga Posture Prediction: Predicts from 82 different Yogasana classes using a trained deep learning model.
• 🧩 Pose Correction (WIP): Compares user landmarks to ideal posture for improvement suggestions.
• ⏱️ Real-Time Feedback: Provides instant accuracy and text feedback on the user’s yoga posture.
• 🖥️ Interactive User Interface: Webcam integration, image/video uploads, audio & text feedback.

🛠 Tech Stack

• Python, Flask
• TensorFlow / Keras
• MediaPipe
• OpenCV
• HTML/CSS/JS (for frontend)

🚀 Getting Started

🔧 Installation

1. Clone the repository:

   git clone https://github.com/anmolkhurana490/Yoga-Posture-Recognition-and-Correction-System.git
   cd Yoga-Posture-Recognition-and-Correction-System

2. Create a virtual environment (optional):

   python -m venv venv
   source venv/bin/activate  # or venv\Scripts\activate on Windows

3. Install dependencies:

   pip install -r requirements.txt

4. Run the app:

   python app.py
   Visit http://localhost:5000 in your browser.

📷 Demo (Coming Soon)

📌 Project Status

• ✅ Yoga Posture Prediction
• ✅ User Interface
• 🛠️ Pose Correction Module (in progress)
• 🛠️ Feedback Mechanism (in progress)

🤝 Contribution

We welcome contributions to enhance this project. See CONTRIBUTING.md for details.

📄 License

This project is licensed under the MIT License.

👏 Acknowledgements

Special thanks to all contributors for their efforts and support!