A Critical Review on Video-Based Continuous Sign Language Recognition

DOI

10.2991/978-94-6463-858-5_161How to use a DOI?

Keywords

Sign language recognition; deep learning; computer vision; natural language processing; SLR datasets

Abstract

Sign language bridges communication gaps, enabling hearing impaired people to understand and connect among themselves. Sign language recognition (SLR) is an automated algorithm that translates hand gestures from hearing impaired into text for facilitating interactions with normal people. In recent years with the explosion of research in technologies like computer vision, deep learning and natural language processing, significant advancements have been made in SLR, improving its accuracy and real-world applicability. Specifically, Continuous Sign Language Recognition (CSLR) is a challenging task as it aims to translate video captured gestures into meaningful text sequentially. Unlike word level sign recognition, CSLR should handle complex spatial-temporal dependencies, coarticulation effects, and variations in signer style. This paper provides a critical review of recent advances in CSLR, focusing on deep learning-based approaches, dataset challenges, feature extraction techniques, and evaluation metrics. We conclude the review by providing potential future research directions based on the limitations in the current methodologies.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Bondalapati SivaKumari
AU  - Vijaya Raghavan
PY  - 2025
DA  - 2025/11/04
TI  - A Critical Review on Video-Based Continuous Sign Language Recognition
BT  - Proceedings of International Conference on Computer Science and Communication Engineering (ICCSCE 2025)
PB  - Atlantis Press
SP  - 1940
EP  - 1955
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-858-5_161
DO  - 10.2991/978-94-6463-858-5_161
ID  - SivaKumari2025
ER  -