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{194604,
        author = {Mona Warkad and Avni Mirani and Vinay Vaidya and Vaibhav Pundekar and Disha Joshi and Dr.A.A.Gurjar},
        title = {A Real-Time Bidirectional Smart Glove System for Indian Sign Language Translation Using Magnetic Sensing and Hybrid Vision Architecture},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {4670-4679},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194604},
        abstract = {Communication barriers between deaf and hearing individuals often limit effective interaction in daily life. According to global health reports, millions of people worldwide experience hearing loss, and many rely on sign language as their primary means of communication [11]. However, communication becomes difficult when interacting with individuals who are unfamiliar with sign language. This paper presents a real-time bidirectional smart glove system designed to facilitate communication between deaf and hearing users through automatic translation of Indian Sign Language (ISL) gestures. The proposed glove integrates Hall effect sensors mounted on the fingers and a palm-mounted magnet to detect finger bending through variations in magnetic field strength. An MPU6050 inertial measurement unit (IMU) is incorporated to capture hand orientation and dynamic motion. Sensor data is processed using an ESP32-S3 microcontroller, which performs real-time gesture recognition and transmits recognized gestures via Bluetooth Low Energy (BLE) to a receiver device equipped with an LCD display and response buttons. The receiver device enables hearing users to send predefined responses back to the glove, allowing bidirectional communication. In addition, a web-based fallback communication interface using MediaPipe hand tracking technology [5] and speech-to-text functionality is implemented to ensure communication continuity in case of hardware failure. Experimental evaluation conducted on a dataset of 970 gesture samples across ten ISL gestures achieved an average recognition accuracy of 94.4%, demonstrating the effectiveness of the proposed system as a cost-effective assistive communication solution for deaf and hearing individuals.},
        keywords = {Smart Glove, Indian Sign Language (ISL), Gesture Recognition, Hall Effect Sensors, ESP32-S3, Assistive Communication Technology, Bidirectional Communication System},
        month = {March},
        }