Virtual Assistance for Disabled People

Communication with others is no longer a hardship for the Blind, Deaf, and Dumb. They struggle to communicate effectively with conventional people. They struggle to obtain work and maintain traditional lifestyles. In this work, it provides a two-way smart communication system for the Blind, Deaf, and Dumb, as well as for normal individuals. The system consists of two major parts: Our hardware technology allows Blind, Deaf, and Dumb individuals to communicate with a normal person using Kannada Language, while our Android application allows non-sign language users to quickly answer. This assures a two-way smart communication system, making life less demanding for them. The dynamic hand skeleton data have become increasingly attractive to widely studied for the recognition of hand gestures that contain 3D coordinates of hand joints gestures by extracting all possible types of skeleton-based features. This project used two graph-based neural network channels in our multi-branch architectures and one general CNN-neural network channel.