An Insight for Visually Impaired using AI Techniques

Open Access

Year : 2021 | Volume : | Issue : 2 | Page : 1-8
By

    Amal K.Santhosh

  1. Natheera Beevi M

  2. Lekshmi S.S.

  1. Student, Department of Master of Computer Applications, Thangal Kunju Musaliar College of Engineering Kollam, Kerala Technological University, Kerala, India
  2. Professor, Department of Master of Computer Applications, Thangal Kunju Musaliar College of Engineering Kollam, Kerala Technological University, Kerala, India

Abstract

We know that the life of blind people is very risky. They always need an assistance or another person for helping them.In this project we introduce AI spectacles for blinds, which will help them to find what is happening in front of them and they will be able to find their own things without any help. In this proposed system,weareusing a real time object detection using YOLOv3 model.‘You only look once’, or YOLO, is one of the fastest object detection algorithms out there. Despite the fact that it is not, at this point,the most exact item identification
alculation, it is a generally excellent decision when you need continuous location, without loss of a lot of exactness. Aroute collaborator for the outwardly debilitated individuals utilizing object identification and text to discourse. The present study “An Insight for visually impaired using AI techniques”,suggeststhe spectacles consistingof an input camera and a part of headset. The working of the AI spectaclesis such that the objects and obstacles in front of blind person are captured by the camera,detected,recognized,convertedinto voice and then passedthroughheadsets.

Keywords: YOLOv3, Google text to speech, Raspberry Pi, Darknet NN-Pack

[This article belongs to Journal of Artificial Intelligence Research Advances(joaira)]

How to cite this article: Amal K.Santhosh, Natheera Beevi M, Lekshmi S.S. An Insight for Visually Impaired using AI Techniques joaira 2021; 8:1-8
How to cite this URL: Amal K.Santhosh, Natheera Beevi M, Lekshmi S.S. An Insight for Visually Impaired using AI Techniques joaira 2021 {cited 2021 Jun 20};8:1-8. Available from: https://journals.stmjournals.com/joaira/article=2021/view=97340

Full Text PDF Download

Browse Figures

References


Regular Issue Open Access Article
Volume 8
Issue 2
Received May 11, 2021
Accepted May 20, 2021
Published June 20, 2021