Scholarlink

<p>Sign language recognition (SLR) systems continue to face significant challenges in accurately interpreting dynamic gestures, particularly for underrepresented languages like Kannada sign language (KSL). This study presents a novel hybrid deep learning architecture that synergistically combines convolutional neural networks (CNNs), hand keypoints (HKPs), long short-term memory (LSTM) networks, and transformers to achieve robust spatial-temporal-contextual learning for KSL recognition. Developed on a newly curated dataset of 1080 medical-domain KSL gestures, our model addresses critical gaps in dataset diversity and model generalizability. The proposed framework demonstrates superior performance with 97.6% training accuracy, 96.75% validation accuracy, and 81% testing accuracy on unseen data—outperforming conventional CNN-LSTM (46%) and HKP-LSTM (71%) baselines. By hierarchically integrating CNN-extracted spatial features, HKP-derived structural priors, LSTM-processed temporal dynamics, and Transformer-modeled long-range dependencies, this work establishes a new benchmark for KSL recognition while providing a scalable solution for real-world healthcare and assistive technology applications.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Comparative Study of Hybrid Deep Learning Models for Kannada Sign Language Recognition

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月24日

查看全文
  • Gurusiddappa Hugar,
  • Ramesh M. Kagalkar,
  • Abhijit Das

摘要

Sign language recognition (SLR) systems continue to face significant challenges in accurately interpreting dynamic gestures, particularly for underrepresented languages like Kannada sign language (KSL). This study presents a novel hybrid deep learning architecture that synergistically combines convolutional neural networks (CNNs), hand keypoints (HKPs), long short-term memory (LSTM) networks, and transformers to achieve robust spatial-temporal-contextual learning for KSL recognition. Developed on a newly curated dataset of 1080 medical-domain KSL gestures, our model addresses critical gaps in dataset diversity and model generalizability. The proposed framework demonstrates superior performance with 97.6% training accuracy, 96.75% validation accuracy, and 81% testing accuracy on unseen data—outperforming conventional CNN-LSTM (46%) and HKP-LSTM (71%) baselines. By hierarchically integrating CNN-extracted spatial features, HKP-derived structural priors, LSTM-processed temporal dynamics, and Transformer-modeled long-range dependencies, this work establishes a new benchmark for KSL recognition while providing a scalable solution for real-world healthcare and assistive technology applications.