Copyright © 2025 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{188128,
        author = {Harshvardhan Pawar and Nikhil Prajapati and Gauri Ghuge and Siddharth Chandra},
        title = {Enhancing Accessibility for People with Disabilities},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {476-482},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=188128},
        abstract = {This paper presents a platform designed to en-hance accessibility for individuals with visual impairments by providing detailed image descriptions and text-to-speech capabilities. The system integrates features from object de-tection and convolutional neural networks (CNN) to generate accurate and context-aware captions. OCR-based text extrac-tion is employed to enhance descriptions of images contain-ing text, and a large language model (LLM) refines these out-puts to produce more accurate and comprehensive descrip-tions. Additionally, a real-time question-answering mecha-nism enables users to interact with the model for situational understanding. The platform prioritizes lightweight imple-mentation to ensure compatibility with low-end devices, pro-moting accessibility for a wider audience. Development was guided by user feedback and collaboration with accessibility experts, emphasizing iterative improvement and user-centric design. This work aims to empower visually impaired indi-viduals by enabling seamless interaction with visual content and surroundings, fostering inclusivity in both academic and daily life contexts.},
        keywords = {Accessibility, Image Captioning, Text-to-Speech, OCR, Real-Time Systems},
        month = {December},
        }