Affordable voice assistive intelligent glass for visually impaired people in perspective of Bangladesh

Abstract

This paper describes design of affordable intelligent glass for visually impaired. A significant number of people are visually impaired or blind among the total population of Bangladesh. Most of them relied on others directly or indirectly which makes their life challenging. In terms of academic and social perspective, they lag behind from their fellow mates. To help these people and lead a better life, artificial intelligent glasses can play a vital role in today’s world. Through this smart glass visual system will convert into an audible system in real time by using a single board computer. Convolutional neural network has been introduced to help visually impaired people to classify objects. Moreover, text recognition will be available for recognizing and reading Bangla as well as English text. With the help of voice command users might be able to control electrical gadgets and be able to communicate with caregivers through mobile app.

Description

Cataloged from PDF version of thesis.
Includes bibliographical references (pages 84-88).
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Electrical and Electronic Engineering, 2021.

Keywords

Smart glass, Raspberry pi 4, Deep learning, Image classification, Speech processing, Convolutional neural network, Optical character recognition, Sensor, App

Citation

Endorsement

Review

Supplemented By

Referenced By