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{191981,
        author = {Priya Koshle and Vinay Pandey},
        title = {An Efficient Angle-Based Sign Language Recognition Framework with Robust Performance Analysis},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {8882-8892},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=191981},
        abstract = {Sign language recognition (SLR) is vital in the barriers of communication between hearing-impaired community and non-signers. Several vision-based deep learning solutions, however, are computationally costly, vulnerable to environmental change, and do not scale to real-time operation whereas sensor-based systems require intrusive and expensive hardware. This paper demonstrates an effective angle-based sign language recognition algorithm which takes advantage of discriminative hand-angle characteristics to classify gestures with high accuracy and reliability. Biomechanically meaningful angular descriptors that are invariant to scale, illumination, and background clutters are used to represent hand gestures (e.g., finger joint angles, palm position, hand-to-ground position) which are biomechanically meaningful. A preprocessing pipeline which includes normalization, outlier elimination and dimensionality analysis is applied in a structured way so as to enhance feature stability and the ability to separate the classes. The resulting angle-based representations are both trained on machine learning and deep learning models. A large-scale sign language experiment proves to be highly recognized with high robustness to hand rotation, variations of finger spread, and inter-user variations. Reliability of real-time assistive applications is ensured by means of confusion and robustness analyses.},
        keywords = {Sign Language Recognition, Angle-Based Features, Hand Gesture Classification, Machine Learning, Robustness Analysis, Real-Time Assistive Systems},
        month = {February},
        }