Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{199764,
        author = {Leena Shahare and Aastha Kadam and Poonam Fegade},
        title = {Real-Time Smart Vision Assistant for Visually Impaired using YOLOv8, OCR and Speech Interaction},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {15312-15317},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199764},
        abstract = {People who are visually impaired might have a hard time being independent. It becomes impossible to see the surrounding things, read the printed text, and learn about the circumstances. Conventional assistive devices, comprising white cane and Braille, provide weak context and lack the ability to interpret visual scenes in action. However, advancements in Artificial Intelligence, Deep Learning and Computer Vision have produced intelligent assistive technologies that convert visual data into meaningful audio output.
This paper presents the Real-Time Smart Vision Assistant which is composed of YOLOv8, OCR, multilingual language translation, and speech to help the visually impaired. The system uses a camera to capture real-time images and feeds them to deep learning algorithms for object detection and text extraction from printed materials such as books, labels, signaling boards etc. After the extraction, the generated output is converted into speech using TTS technology for English, Hindi and Marathi language. The system uses edge computing architecture to enhance response time and protect data privacy.
According to the experimental evaluation, YOLOv8 detects objects more accurately than any previous detection model. Improving accessibility and independence of the visually impaired by integrating OCR and multilingual speech interaction users. The suggested technology can serve as a low-cost assistive device to understand environment.},
        keywords = {Assistive Technology, Computer Vision, YOLOv8, Optical Character Recognition, Deep Learning, Text-to-Speech, Accessibility.},
        month = {April},
        }