Indian Sign Language Recognition System

Overview

Automatic Recognition and Generation of Indian Sign Language (ARGISL) is a joint colaborative project between Computer Science Department, RKMVERI, Belur and FDMSE, RKMVERI, Coimbatore. The aim of this project is to build a Indian Sign Language recognition and generation system which could be helpful for the Indian deaf community. Initially we started with 2002 most commonly daily used words in deaf community. We have collected the data from RKMVERI Coimbatore campus and built a recognition model which performs around 93% accurately. If you like our research work, you can support us here.

Indian Sign Language Word Dictionary

Recognition Demo

Processing...

Top 5 Results

Related Publications

Hierarchical Windowed Graph Attention Network and a Large Scale Dataset for Isolated Indian Sign Language Recognition

Suvajit Patra, Arkadip Maitra, Megha Tiwari, K. Kumaran, Swathy Prabhu, Swami Punyeshwarananda, Soumitra Samanta
ARXIV, 2024

Paper (arXiv) Code Demo Dataset Cite @misc{patra2024hierarchicalwindowedgraphattention, title={Hierarchical Windowed Graph Attention Network and a Large Scale Dataset for Isolated Indian Sign Language Recognition}, author={Suvajit Patra and Arkadip Maitra and Megha Tiwari and K. Kumaran and Swathy Prabhu and Swami Punyeshwarananda and Soumitra Samanta}, year={2024}, eprint={2407.14224}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2407.14224}, }

Acknowledgement

We would like to thank all the perticipants who have perticipated in our data collection process and the audio-visual unit of RKMVERI, Coimbatore for their technical support. We also like to thank VECC, Kolkata for parly supporting this project.