Sign language recognition
The neural network of this system used extracted image features as input and it was trained using back-propagation algorithm to recognize which letter was the given letter with accuracy of respectively 70% and 85% with two proposed classifiers.
Abstract
Millions of people around the world suffer from hearing disability. This large number demonstrates the importance of developing a sign language recognition system converting sign language to text for sign language to become clearer to understand without a translator. In this paper, a sign language recognition system using Backpropagation Neural Network Algorithm is proposed based on American Sign Language. The neural network of this system used extracted image features as input and it was trained using back-propagation algorithm to recognize which letter was the given letter with accuracy of respectively 70% and 85% with two proposed classifiers.