DEEP-SEE FACE A Mobile Face Recognition System Dedicated to Visually Impaired People
To develop an assistive device designed to improve cognition, interaction, and communication of visually impaired people in social encounters.
A novel assistive device based on computer vision algorithms and offline-trained deep convolutional neural network with a face recognition module. The existing system is able to identify in real-time, from video streams, a set of characters, which can be pre-defined by the user and which may correspond to either familiar people that the visually impaired user may encounter in real life or to celebrities appearing in media streams using a laptop or computer.
We propose a face detection and recognition for the visually impaired user by eliminating the need of a computer or a laptop. By the advancement of the processing power of the IoT devices and the reduced costs will help to implement high processing time / power algorithms to IoT devices. We implement an advanced face detection and recognition system which can run in a small form factor single board computer.