Dynamic Sign Language Recognition with Hybrid CNN-LSTM and 1D Convolutional Layers

Our study presents a novel approach for sign language recognition (SLR) using Convolutional Neural Networks (CNN), 1D convolutional layers, and Long Short-Term Memory (LSTM) networks. By integrating CNN and 1D convolutional layers to capture temporal patterns and LSTM layers for handling long-term dependencies, our model achieves accurate classification of sign language gestures. We also discuss future directions, including expanding the model's recognition capabilities to other sign languages and enabling user customization, to enhance inclusivity and user-friendliness within the sign language community. This work contributes to advancing SLR technology and improving communication accessibility for individuals with hearing impairments.