Smart Blind Cane using Machine Learning

Date
2019
Research Supervisor
Editor
Journal Title
Volume
Issue
Journal Title
Journal ISSN
Volume Title
Abstract
The purpose of this report is to present and describe a smart cane for blind and visually impaired people. Our project postulates that a smart blind cane which can alert visually impaired people over hurdles ahead could assist them in walking, avoiding accidents. The aim of our project is to assist the disable and blind people through the development of a smart blind cane using Machine learning and computer vision, invoking convolutional neural networks to detect objects, and stereo vision to get distance measurements. However we could not implement the Stereo vision part, thus failing to calculate the distance. But, we succeeded in “Object Recognition and voice output.” Upon recognizing the object, it gives a voice output of what lies ahead. Many of the blind canes offer limited capabilities, some can achieve the required precision in part. However, none of these fulfill all the necessary and fundamental features that would make the device ideal in its use. Our cane aims to highlight the improvements, depicting the advancement of technology and fully ensuring the safety of the blind and visually impaired people.
Description
Keywords
Citation
Department Name
Electrical and Computer Engineering
Publisher
North South University
Printed Thesis
DOI
ISSN
ISBN