International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Automated Sign Language Recognition using Deep Learning Techniques |
|---|---|
| ABSTRACT | This project presents a Sign Language Recognition System designed to interpret static hand gestures representing the 26 letters of the English alphabet using American Sign Language (ASL). Developed using Google’s Teachable Machine, the model leverages transfer learning and a CNN-based architecture to recognize hand signs from real-time camera input and translate them into text. Trained on multiple image samples under controlled conditions, the system demonstrates high accuracy and responsiveness, even with slight variations in lighting and hand orientation. Aimed at being low-cost, accessible, and efficient, it holds promise for use in educational and assistive settings. Future enhancements may include dynamic gesture recognition, sentence-level translation using NLP, and mobile app development for improved accessibility. |
| AUTHOR | PROF. TUSHAR SURWADKAR, PROF. JUNAID MANDVIWALA, KASHAF KHAN, SALINA SHEKASAN, SADAF SHAIKH, KAIF KHAN |
| PUBLICATION DATE | 2025-10-27 |
| VOLUME | 175 |
| DOI | DOI:10.15680/IJIRCCE.2025.1310020 |
| pdf/20_Automated Sign Language Recognition using Deep Learning Techniques.pdf | |
| KEYWORDS |
