International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | AI Powered Assistance System for Visually Impaired |
|---|---|
| ABSTRACT | Safe navigation remains a major challenge for visually impaired individuals, particularly in indoor environments where obstacles such as furniture, equipment, and people may obstruct movement. Conventional mobility aids such as white canes provide only limited tactile feedback and do not offer information about the surrounding environment before physical contact occurs. This project presents an AI Powered Navigation Assistance System for Visually Impaired that utilizes computer vision techniques to detect obstacles and provide voice guidance. The system processes real-time visual input from a camera and applies an object detection model to identify objects present in the environment. Detected objects are analyzed to determine whether they lie within the user’s path of movement, and relevant voice alerts are generated using a text-to-speech module. The system has been implemented using Python and the YOLOv8n object detection model for real-time detection and audio feedback. In addition, a mobile application interface developed using Android Studio with Gemini API integration has been designed to illustrate how the system can be extended to smartphone-based accessibility. Experimental observations demonstrate that the system can successfully identify obstacles and generate appropriate audio guidance. The mobile application component further demonstrates the feasibility of integrating the navigation assistance functionality into mobile devices. The proposed system highlights the potential of combining artificial intelligence, computer vision, and mobile technologies to enhance accessibility and independent mobility for visually impaired users. |
| AUTHOR | PROF. D.C.PARDESHI, MRUNAL BHOSALE, TANISHKA GAIKWAD, AARYA TAWARE, VED TUPE Guide, Department of Artificial Intelligence & Machine Learning, AISSMS's Polytechnic, Pune, Maharashtra, India Department of Artificial Intelligence & Machine Learning, AISSMS's Polytechnic, Pune, Maharashtra, India |
| VOLUME | 182 |
| DOI | DOI: 10.15680/IJIRCCE. 2026.1403069 |
| pdf/69_AI Powered Assistance System for Visually Impaired.pdf | |
| KEYWORDS | |
| References | [1] Mrs. Keerthiga.V, Anne P.S, Bhavani. G, “VISIONSPEAK: Object Detection and Voice Assistance for Visually Impaired People,” International Journal of Advanced Research in Computer and Communication Engineering (IJARCCE), 2025. DOI: 10.17148/IJARCCE.2025.14479. Available: https://ijarcce.com/wp-content/uploads/2025/05/IJARCCE.2025.14479.pdf [2] R. Gawande, Shraddha P. Mankar, D. Sankhala, N. Watpal, S. Vispute, “Android Based Object Detection System for Visually Impaired,” International Journal for Research in Applied Science & Engineering Technology (IJRASET), 2024. DOI: https://doi.org/10.22214/ijraset.2024.58593. Available: https://www.ijraset.com/best-journal/android-based-object-detection-system-for-visually-impaired-587 [3] Yogesh M, Dr. Madhu H.K., “AI Eyes: A Real-Time Assistive Mobile Application for Visually Impaired People Using Object Detection,” International Journal of Advanced Research in Computer and Communication Engineering (IJARCCE), 2026. DOI: 10.17148/IJARCCE.2026.151132. Available: https://ijarcce.com/wp-content/uploads/2026/01/IJARCCE.2026.151132-ai.pdf [4] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. [5] Glenn Jocher et al., “YOLOv8: Ultralytics Object Detection Model,” Ultralytics Documentation, 2023. Available: https://docs.ultralytics.com/ |
