Assistant for Visually Impaired using Computer Vision

In this paper, a virtual assistant for the visually impaired is built using various technologies such as computer vision, object recognition, emotion detection, and text-to-speech using a micro-computer in order to describe the scene around as a narrative to the user. We generate an audio narrative by converting the scenes obtained by visual data in front of user to text which describes the important objects in the scene in audio format. Possible future ventures into involvement of various sensors to perform SLAM based navigation along with barcode reading.