Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{206832,
        author = {Shravya and Sudarshan K and Ashvitha Fernandes and Jothsna P S and Krithi},
        title = {The Language of Hand Gesture in Bharatnatyam},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {no},
        pages = {618-623},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206832},
        abstract = {This paper introduces a new computer vision and deep learning framework that can automatically recognize and analyze Hasta Mudras (hand gestures) used in Bharatanatyam, a classical Indian dance form. In the past, analyzing Mudras, which are a non-verbal language that is important for expressive storytelling, was a manual and subjective process. We use a two-stage pipeline in our proposed system to deal with the problems of scale, translation, and rotation invariance. The Media Pipe Hands model first finds 21 important hand landmarks in real time. Second, a custom feature engineering process normalizes these raw coordinates to the wrist to make an 84-dimensional invariant feature vector. A lightweight Multi-Layer Perceptron (MLP) model then sorts this vector. The system has a high classification accuracy and a fast inference speed, which shows that it can be used in real time for training and digital archiving of cultural heritage.},
        keywords = {Bharatanatyam, Mudra recognition, Hand gesture analysis, Computer Vision, Media Pipe, Deep Learning, and Multi-Layer Perceptron (MLP) are some of the words used.},
        month = {July},
        }