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{192682,
        author = {MADUGUNDU AJAY and THODA PREM KUMAR and PARIGELA RAHUL KUMAR and Nellibanda Charan and Dr Y Narasimha Reddy and Dr. P. Veeresh},
        title = {SignVision: Real-Time Sign Language Recognition Using Computer Vision},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {9},
        pages = {1944-1949},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=192682},
        abstract = {The sociolinguistic isolation of the hearing and speech-impaired population can be considered to be a pertinent impediment in the development of the concept of an ‘information society’. With the monumental developments occurring in the field of ‘Computer Vision’ and ‘Deep Learning’ technologies, the process of coping up with the complex nature of the “high-dimensionality” in “hand-related” operations remains a daunting issue in the development of the process of ‘Real Time Sign Language Recognition’. This paper proposes to emphasize the “extensive technological framework” of the “SignVision” system designed with the objective to facilitate the process of ‘Real Time Translation’ of ‘ASL’. This paper will also provide detailed information about the concept of the “Master Bounding Box” algorithm in the context of spatial orchestration of “hand-related” skeleton data.
Using the Conventional Neural Network (CNN) performance optimization model for inference at the edge and MediaPipe hand tracking technology with an accuracy of up to one millimeter, it was possible to achieve 91.4 percent accuracy at the word level with a vocabulary of 14 words. This is where current research is heading, extending well beyond translation to a more viable solution for interview preparedness and interview professionalism in Inclusive.},
        keywords = {Artificial intelligence, Computer vision, Sign language recognition, Deep learning, CNN, MediaPipe, Master bounding box, Skeletal tracking.},
        month = {February},
        }