WSEAS Transactions on Computers
Print ISSN: 1109-2750, E-ISSN: 2224-2872
Volume 18, 2019
Hella - A Smart Reading Bot
Authors: , ,
Abstract: The main objective of this project is to present a smart reading bot for visually impaired people. According to World Health Organization (WHO), 81% are visually impaired who live in developing countries. Nowadays Human communication is mainly focused on text and speech. To read the text a human needs a vision. The existing method is still incomplete to meet their requirements, so current technology is implemented in the project to perform their day to day activities irrespective of their impairments. In order for the humans to be updated with the current trend, a smart reading bot is implemented. This system consists of a camera interfaced with Raspberry Pi for processing the text in the form of image capturing. The camera is used to capture the image of both handwritten and printed text. The raspberry pi makes use of python programming and libraries to perform image to text conversion and text to speech conversion. The bot not only reads the printed or handwritten text and gives the output in audio form by using Text to Speech synthesis. Also search for the word given by the user in the form of voice is recognized and particular word is searched in the line of text. Additionally, it helps to find the meaning of the specific word pronounced by the user, both searching and finding the meaning is done through speech recognition methodology, and all these outputs are converted into audio output (Speech). Searching the word gives the output as whether the word is present or not. The main advantage of this project is the captured image and audio will not get stored in the Raspberry Pi it will get directly uploaded in AWS server called S3 bucket which in returns give the public URL for accessing the image and audio for the use of text to speech conversion, image to text and all other features done by the Raspberry Pi. The future technology aims at providing a portable setup with battery backup which can be used anywhere and at any time. The application of this proposed system mainly focuses in the areas where the information and notices are to be read like in auditoriums, libraries and offices. The assistant is applicable for visually impaired people as well as for normal people in order to increase their level of comfort.
Search Articles
Keywords: Text to speech, Image to Text, Image Recognition, Raspberry Pi, Speech output, Speech synthesis, S3 bucket, AWS
Pages: 101-106
WSEAS Transactions on Computers, ISSN / E-ISSN: 1109-2750 / 2224-2872, Volume 18, 2019, Art. #13