Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.22011 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908611447357440 |
|---|---|
| author | Takouchouang, Fraisse Sacré Vinh, Ho Tuong |
| author_facet | Takouchouang, Fraisse Sacré Vinh, Ho Tuong |
| contents | Sign languages play a crucial role in the communication of deaf communities, but they are often marginalized, limiting access to essential services such as healthcare and education. This study proposes an automatic sign language recognition system based on a hybrid CNN-LSTM architecture, using Mediapipe for gesture keypoint extraction. Developed with Python, TensorFlow and Streamlit, the system provides real-time gesture translation. The results show an average accuracy of 92\%, with very good performance for distinct gestures such as ``Hello'' and ``Thank you''. However, some confusions remain for visually similar gestures, such as ``Call'' and ``Yes''. This work opens up interesting perspectives for applications in various fields such as healthcare, education and public services. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_22011 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Reconnaissance Automatique des Langues des Signes : Une Approche Hybridée CNN-LSTM Basée sur Mediapipe Takouchouang, Fraisse Sacré Vinh, Ho Tuong Computer Vision and Pattern Recognition Artificial Intelligence Sign languages play a crucial role in the communication of deaf communities, but they are often marginalized, limiting access to essential services such as healthcare and education. This study proposes an automatic sign language recognition system based on a hybrid CNN-LSTM architecture, using Mediapipe for gesture keypoint extraction. Developed with Python, TensorFlow and Streamlit, the system provides real-time gesture translation. The results show an average accuracy of 92\%, with very good performance for distinct gestures such as ``Hello'' and ``Thank you''. However, some confusions remain for visually similar gestures, such as ``Call'' and ``Yes''. This work opens up interesting perspectives for applications in various fields such as healthcare, education and public services. |
| title | Reconnaissance Automatique des Langues des Signes : Une Approche Hybridée CNN-LSTM Basée sur Mediapipe |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2510.22011 |