An intelligent Assistant for the Visually Impaired and blind people using machine learning

Abstract

People who suffer with visual impairment and blindness face numerous challenges in their daily lives. For a visually impaired person, particularly the one with complete vision loss; the biggest challenge is to navigate around places. This study proposes a smart implementation assistance approach which aims to improve the lives of visually impaired and blind people in terms of safety, social inclusion, and navigation. Although there are many visually impaired assistant devices available in market but there is not one that is low-cost, ultra-portable, exceptionally reliable and capable of detecting objects from large distance with accuracy. The proposed system uses computer vision and image recognition along with machine learning for experimental purpose. In this work we used a high quality RGB camera with 1024x768 pixels resolution capturing live video of the surroundings. The images extracted from captured videos identified using object detector and the corresponding names of the detected images saved as texts for further processing. Ultimately text to speech engine, convert the names of the identified objects into audible sound and is provided to the visually impaired person. The primary motive to conduct this research is to offer mobility independence to those who are visually impaired.