Bharatanatyam Pose Perfection: Deep Learning vs. Meta-Learning & Real-Time Pose Evaluation with MediaPipe and OpenCV

Bharatanatyam is renowned for its ability to narrate stories and express emotions through a complex interplay of facial expressions, hand gestures, and body postures. However, the sheer complexity of these dance movements poses a significant challenge in terms of capturing and evaluating them with precision. This work seeks to leverage the power of computer vision techniques, such as MediaPipe and OpenCV, as well as deep learning and meta-learning models, to create a system that can accurately detect and analyze Bharatanatyam dance poses in real-time. By providing dancers with immediate feedback on their performance, the work aims to enhance the understanding and appreciation of this rich cultural heritage, ensuring that the divine stories and emotions conveyed through Bharatanatyam are presented with the utmost clarity and authenticity for virtual learning as well. The deep learning model (CNN) achieved 95% accuracy while the meta-learning model (Siamese Network) attained 90% accuracy. These results highlight the deep learning model's higher accuracy and the meta-learning model's efficient learning process. By providing dancers with immediate performance feedback, this system enhances the understanding and appreciation of Bharatanatyam, ensuring its cultural narratives are presented with clarity and authenticity.