Abstract:

This paper proposes a Recognition system for Sign Language using a Convolutional Neural Network (CNN) that recognizes Sign Language digits and alphabets and converts them into speech. This system can help bridge the communication gap between deaf-dumb individuals and the general public. Learning Sign Language can be challenging, and therefore, the proposed system uses an American Sign Language (ASL) dataset to achieve a training accuracy of 99.8%.

Description:

Convolutional Neural Network (CNN), Python, Google Collab, Google Text to Speech, Open CV, Tensorflow, Sign Language Recognition