International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 04 | Apr 2024
p-ISSN: 2395-0072
www.irjet.net
DEVELOPING AN INTELLIGENT SYSTEM FOR MULTILINGUAL VISUAL TO AUDIO CONVERSION FOR PERSONS WITH VISUAL IMPAIRMENTS USING ARTIFICIAL INTELLIGENCE Dr. S RAJAN1, Ms. P SUBHAVARSHINI2, Ms. A SOUNDARYA3, Mr. S SAKTHIVEL4, Mr. J VIJAYAKUMAR5 1
Professor, Dept. of ECE, Velalar College of Engineering and Technology, Thindal, Erode, Tamilnadu, India. B.E Final Year Students, Dept. of ECE, Velalar College of Engineering and Technology, Thindal, Erode, Tamilnadu, India. ------------------------------------------------------------------------***-----------------------------------------------------------------------2,3,4,5
deserve equal access to information in all of them. Moreover, the internet has enabled global connectivity, making it imperative for assistive technologies to break down language barriers. This project aims to provide an overview of intelligent systems for multilingual visual-toaudio conversion for persons with visual impairments.
ABSTRACT According to the World Health Organisation, around 40 million people in the world are blind, while another 250 million have some visual impairments. Reading poses a significant challenge for them. To address this, an automatic reader for Visually Impaired People is developed. It works by capturing text from documents using a webcam and converting it into digital format through Optical Character Recognition (OCR). The text is extracted from the visual image and converted to audio output, in which one can hear through the speaker. In this, it proposed an intelligent system for multilingual visual-toaudio conversion to facilitate audio accessibility for persons with visual impairments. It aims to serve both visually impaired people and illiterate people. The system can process visual images in multiple languages and generate audio descriptions in the user’s preferred language. The audio descriptions are designed to be concise, descriptive, and accurate, providing users with a detailed understanding of the visual image content.
2. PROPOSED SYSTEM An intelligent system for visual-to-audio conversion for persons with visual impairments is a technology that converts visual information, such as images, graphs, and videos, into audio signals, so that individuals with visual impairments can comprehend the visual information through sound. The system uses computer vision and machine learning algorithms to analyze the visual content and generate a corresponding audio description that describes the relevant details of the visual information.
KEYWORDS Raspberry Pi 4 Model B, Optical Character Recognition, OpenCV, Raspbian, Python, Pytesseract, Real VNC Viewer App 1. INTRODUCTION Visual impairment is a condition that affects a significant percentage of the global population. People with visual impairments face significant challenges in accessing and interpreting visual information, particularly in a world that relies heavily on visual communication. To address this challenge, intelligent systems for multilingual visualto-audio natural language processing technologies analyze visual media and provide audio descriptions of their content. By converting visual information into audio, these systems enable visually impaired people to access and understand visual media content that would otherwise be inaccessible to them. Many individuals with visual impairments are proficient in multiple languages, and they © 2024, IRJET
|
Impact Factor value: 8.226
Figure 1 Block Diagram of Proposed System The above Figure 1 shows the Block Diagram of the system, the image input is given to the web camera the |
ISO 9001:2008 Certified Journal
|
Page 2156