Mediapipe-Powered SVM Model for Real-Time Kuchipudi Mudras Recognition

In the fields of computer vision and gesture recognition, Recognizing Kuchipudi mudras in the real time, a traditional Indian dance form, is one of the challenging tasks. In this research work, an innovative solution was proposed for this problem. Support Vector Machine model along with The Google’s Mediapipe framework are used for the real-time recognition of Kuchipudi mudras. The goal is to build a system that is able to differentiate the complex hand mudras in Kuchipudi performances with good accuracy and efficiency. The methodology includes image capture and preprocessing, extraction of hand landmarks by Mediapipe, as well as training an SVM model on a labeled data set. In addition to the above, real-time testing of the model is performed, and the webcam makes it possible to identify and display predicted mudras almost instantly. The SVM model correctly predicts various Kuchipudi’s mudras. The presented research opens up the expressly possibility of real-time detection of movements in traditional dances and, in the future, can be used as a software module for teaching and grading dancers. I have used the Support Vector Machine technique; it resulted in surprisingly accurate detection of unique hand movements in Kuchipudi.