Open Access Open Access  Restricted Access Subscription or Fee Access

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

Koushal Kumar, Pranav Mappoli

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.

Keywords


Visually impaired, real-time, intelligent assistant, Tensorflow, object recognition

Full Text:

PDF


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information.