Interactive Sign Language Learning System Using Computer Vision and Deep Learning

Murugan, Suganiya and Ali, Mir Kasif and Singari, Dhanvanth and Kumar, S. Pradeep (2024) Interactive Sign Language Learning System Using Computer Vision and Deep Learning. In: 2024 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI), Chennai, India.

Full text not available from this repository. (Request a copy)

Abstract

In an era where communication is key, the gap in accessible tools for those with hearing impairments or speech disabilities is significant. These individuals often face obstacles in education and social interaction due to a heavy reliance on spoken language and a lack of sign language resources. The Interactive Sign Language Learning System (ISLLS) addresses this gap by providing an innovative platform for learning sign language, enhanced with voice output to assist individuals with speech disabilities. This feature allows for auditory feedback alongside visual sign learning, enriching the educational experience. The ISLLS employs advanced technologies like computer vision and deep learning to facilitate sign recognition and text-to-sign conversion. With the new voice output, it further aids those with speech impairments, expanding its inclusivity. This system offers a comprehensive learning tool that caters to a diverse user base, enabling people with speech difficulties to engage more fully with the world. The ISLLS is a significant step towards a more inclusive society, offering a user-friendly platform that not only improves the learning of sign language but also empowers people with speech disabilities to connect and thrive, representing progress in both technology and social inclusivity.

Item Type: Conference or Workshop Item (Paper)
Subjects: Computer Science Engineering > Deep Learning
Domains: Electrical and Electronics Engineering
Depositing User: Mr IR Admin
Date Deposited: 23 Aug 2025 07:03
Last Modified: 23 Aug 2025 07:03
URI: https://ir.vistas.ac.in/id/eprint/10365

Actions (login required)

View Item
View Item