Jump to main content
US EPA
United States Environmental Protection Agency
Search
Search
Main menu
Environmental Topics
Laws & Regulations
About EPA
Health & Environmental Research Online (HERO)
Contact Us
Print
Feedback
Export to File
Search:
This record has one attached file:
Add More Files
Attach File(s):
Display Name for File*:
Save
Citation
Tags
HERO ID
7203541
Reference Type
Journal Article
Title
Deep convolutional Neural Network in Smart Assistant for Blinds
Author(s)
Kapoor, R; Bharathi, A; Sushama, M; ,
Year
2019
Publisher
IEEE
Location
NEW YORK
Book Title
TENCON IEEE Region 10 Conference Proceedings
Page Numbers
1697-1701
Web of Science Id
WOS:000528677800311
Abstract
Increasing pollution and changing life styles has severely affected human health specially our sense organs. More exposure to screen has increased vision related problems even at very early age of life. The developing technologies should be utilized to help the persons with no or very less vision to lead an independent life in society. Computer vision is one such field that can be utilized to develop some cost effective products that can be very useful for these scenarios. The detection and recognition of text from natural image can be very useful for visually imparted persons as well as in various other applications like developing a smart system to help driver in getting voice signal for every road sign, and even warning if we did not follow the one. The proposed work uses deep convolutional neural network to implement a text detection and recognition system that is much simpler and faster as compare to traditional hand crafted feature based methods.
Keywords
Convolutional neural network; deep neural network
Conference Name
IEEE Region 10 Conference on Technology, Knowledge, and Society (TENCON)
Conference Location
Kochi, INDIA
Home
Learn about HERO
Using HERO
Search HERO
Projects in HERO
Risk Assessment
Transparency & Integrity