Sign Language to Text Conversion Using LSTM Model

Sign language is a crucial medium of communication for individuals with hearing impairments. However, the lack of efficient tools for converting sign language into text limits the accessibility of information for this community. In this paper, we propose a novel approach for sign language to text conversion using Long Short-Term Memory (LSTM) neural networks. LSTM networks are well- suited for sequential data processing, making them an ideal candidate for capturing the temporal dependencies inherent in sign language gestures. We present the architecture of our LSTM model, discuss the datasets preparation, training methodology, and evaluate the performance of our model through comprehensive experiments. The results demonstrate the effectiveness and feasibility of our proposed approach in accurately translating sign language gestures into text, thereby enhancing accessibility for individuals with hearing impairments.