Android Application for Object Recognition Using Neural Networks for the Visually Impaired

This android application is developed for the visually impaired. It has real-time objection recognition using a camera phone and gives voice output for the recognized object. The application uses a neural network for efficient recognition and quicker response time. The neural networks, similar to the processing of the brain, develop algorithms that can be used to model complex patterns and prediction problems. We have used MobileNets neural network which is used for mobile and embedded vision application.