Transforming Sign Language Through Innovations In Machine Vision

This paper systematically explores the various stages involved in the development of a Sign Language system. To create a system capable of comprehending and interpreting signs, it is essential to train it with an extensive dataset and employ the most effective algorithm available. A fundamental Sign Language Recognition (SLR) system is crafted, focusing on an isolated recognition model. This model relies on vision-based techniques for the detection and recognition of isolated hand gestures. Utilizing a feature extraction and employing Convolution Neural Networks (CNN) for classification, the model achieved an impressive accuracy rate of $\mathbf{9 9 \%}$.