手语自动识别：基于Mediapipe的CNN-LSTM混合方法
Reconnaissance Automatique des Langues des Signes : Une Approche Hybridée CNN-LSTM Basée sur Mediapipe
AI总结：
针对手语边缘化问题，提出基于Mediapipe和CNN-LSTM混合架构的自动手语识别系统，实现实时翻译，平均准确率达92%，为医疗、教育等领域应用开辟前景。
摘要：
手语在聋人社区的交流中起着至关重要的作用，但手语常常被边缘化，限制了聋人获取医疗和教育等基本服务的机会。本研究提出了一种基于混合CNN-LSTM架构的自动手语识别系统，使用Mediapipe进行手势关键点提取。该系统使用Python、TensorFlow和Streamlit开发，提供实时手势翻译。结果显示平均准确率为92%，对于“Hello”和“Thank you”等不同手势表现出非常好的性能。然而，对于视觉上相似的手势（如“Call”和“Yes”）仍存在一些混淆。这项工作为医疗、教育和公共服务等领域的应用开辟了有趣的前景。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
