SLRNet: A Real-Time LSTM-Based Sign Language Recognition System
Fuente:
arXiv
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913896307097600 |
|---|---|
| author | Kamble, Sharvari |
| author_facet | Kamble, Sharvari |
| contents | Sign Language Recognition (SLR) plays a crucial role in bridging the communication gap between the hearing-impaired community and society. This paper introduces SLRNet, a real-time webcam-based ASL recognition system using MediaPipe Holistic and Long Short-Term Memory (LSTM) networks. The model processes video streams to recognize both ASL alphabet letters and functional words. With a validation accuracy of 86.7%, SLRNet demonstrates the feasibility of inclusive, hardware-independent gesture recognition. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_11154 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SLRNet: A Real-Time LSTM-Based Sign Language Recognition System Kamble, Sharvari Computer Vision and Pattern Recognition 68T07 (Artificial Intelligence), 68U10 (Image Processing) Sign Language Recognition (SLR) plays a crucial role in bridging the communication gap between the hearing-impaired community and society. This paper introduces SLRNet, a real-time webcam-based ASL recognition system using MediaPipe Holistic and Long Short-Term Memory (LSTM) networks. The model processes video streams to recognize both ASL alphabet letters and functional words. With a validation accuracy of 86.7%, SLRNet demonstrates the feasibility of inclusive, hardware-independent gesture recognition. |
| title | SLRNet: A Real-Time LSTM-Based Sign Language Recognition System |
| topic | Computer Vision and Pattern Recognition 68T07 (Artificial Intelligence), 68U10 (Image Processing) |
| url | https://arxiv.org/abs/2506.11154 |