Comparative Study Between CNN and LSTM Architectures for Sign Language Recognition

People who suffer from hearing or speaking problems might soon be able to communicate more successfully with the assistance of technology that converts gestures into speech. This project aims to generate appropriate translations. The system utilizes a convolutional neural network, also known as CNN, and Long Short-Term Memory (LSTM) to analyze the temporal and spatial patterns of gestures. The paper seeks to provide a conclusive study between the two stated models for this application and highlights the tremendous value of gesture-driven systems in enabling more immersive human-computer interaction and accessible interfaces for diverse communities.