This is an outdated version published on 2022-11-04. Read the most recent version.

Efficient Multi-Object Identification and Guiding System for Visually Impaired

Authors

  • Kasarapu Ramani , Irala Suneetha , Nainaru Pushpalatha , P. Harish , P. Yugandhar

DOI:

https://doi.org/10.47750/pnr.2022.13.04.139

Abstract

Blind or visually impaired people can experience the surroundings through sound. Navigation based on audio is much helpful. Based on this
principle a prototype with deep learning techniques is developed. Sensor based IoT system finds the presence of the objects and recognition
is done through CSPDarknet-53 along with SPP and PANet for feature extraction and fusion. In addition to this it provides audio output in
multilingual language. The system is designed to provide good accuracy and low latency in recognizing the objects and audio output in local
language. Apart from this, it also provides the distance of the object from the user. The system is designed to recognize even a moving object
with good accuracy.

Downloads

Published

2022-11-04

Versions

Issue

Vol. 13 No. 4 (2022)

Section

Articles

How to Cite

Efficient Multi-Object Identification and Guiding System for Visually Impaired. (2022). Journal of Pharmaceutical Negative Results, 13(4), 1019-1023. https://mail.pnrjournal.com/index.php/home/article/view/2965