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{205626,
        author = {Anupsinh Shivaji Chauhan and Pruthviraj Shinde and Pushkar Yewale and Prof. U. S. Pawar},
        title = {Yoga Mudra Analysis for Specially Enabled People Using NLP},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {9157-9165},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=205626},
        abstract = {Yoga mudras, the symbolic hand gestures integral to traditional yoga practice, play a vital role in balancing energy flow and enhancing concentration, meditation, and healing. How-ever, recognizing and understanding these mudras correctly often requires expert supervision, which limits accessibility for learners—especially those who are hearing or visually impaired—and for individuals practicing remotely. With advancements in artificial intelligence and computer vision, it is now possible to automatically identify such gestures and deliver meaningful interpretations in real time. This paper introduces an AI-based Yoga Mudra Recognition and Multilingual Translation System designed to make yoga learning accessible to hearing and visually impaired individuals. The system uses OpenCV to capture real-time video input and MediaPipe for hand landmark detection. Extracted features are processed by a custom CNN-based model trained on a self-created mudra dataset for precise recognition. Once a mudra is identified, its corresponding description is generated and passed to a multilingual translation and text-to-speech (TTS) module, which translates content from English to Marathi and Hindi. The translated text is displayed for hearing-impaired users, while the TTS output provides auditory assistance for visually impaired users. By integrating computer vision, deep learning, and multilingual communication, the proposed system promotes inclusivity, cultural diversity, and self-guided learning.},
        keywords = {Natural Language Processing (NLP), Convolutional Neural Network (CNN), MediaPipe, Hand Gesture Recognition, Assistive Technology, Specially Enabled People.},
        month = {June},
        }