INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
In the 2019 survey conducted by the Indian Foundation for the Blind, it was observed that a staggering 6.8 trillion people are visually impaired, facing challenges in their daily lives. Recognizing the importance of enabling them to navigate the contemporary world despite their impairments, it becomes imperative to implement measures leveraging emerging technologies. In this context, this paper proposes a novel approach aimed at supporting the visually impaired population by introducing a self-assisted text-to-speech module. This module not only caters to the visually impaired but is also beneficial for individuals without visual impairments who seek a quick conversion of text to speech. The proposed method involves the use of a finger-mounted camera to capture images of printed text. Subsequently, an Optical Character Recognition (OCR) technique is employed to analyze the captured image, comparing it with a predefined dataset for character recognition. The key advantage of this method lies in its ability to significantly reduce the dataset memory requirements for comparison, as it focuses solely on character recognition. The efficacy of the proposed system is simulated using Python simulator software, employing two classification algorithms— Random Forest (RF) and Convolutional Neural Networks (CNN) in conjunction with OCR. This comprehensive approach aims to address the challenges faced by the visually impaired community, enhancing their accessibility to textual information efficiently and inclusively. Index Terms— Accuracy, Precision, Recall, CNN, RF, OCR, Python.
"ASSISTING BLIND READERS: IMAGE TEXT-TO-SPEECH CONVERSION IN PREFERRED LANGUAGE", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.9, Issue 4, page no.825 - 832, April-2024, Available :http://www.ijsdr.org/papers/IJSDR2404116.pdf
Downloads:
000338173
Publication Details:
Published Paper ID: IJSDR2404116
Registration ID:210794
Published In: Volume 9 Issue 4, April-2024
DOI (Digital Object Identifier):
Page No: 825 - 832
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn