Paper Details
Design and Development of Human Identification and Obstacle Detection System for Blind using Machine Learning
Authors
R. Santhiya, K. Praveena Kamal
Abstract
According to the World Health Organization (WHO), there are millions of visually impaired people in the world, either completely or partially, and they face numerous challenges in detecting obstacles and identifying persons around them. Not only has information technology evolved rapidly, but the spatial cognition theory for blind and visually impaired (BVI) people has also made great strides, which has opened up a new opportunity. As a result, this prototype develops the concept of supplying them with a simple and cost-effective solution via artificial vision. This project has proposed a novel framework by utilizing AI, which makes the framework more straightforward to use specifically for the individuals with visual impedances and to help the society. we developed an intelligent system for visually impaired people using a Machine learning (ML) algorithm, i.e., convolutional neural network (CNN) architecture, to recognize the human and scene objects or obstacles automatically in real-time. The proposed system is able to properly recognize humans in complex environments with multiple moving targets, thus providing to the user a complete set of information, namely presence, position and nature of the available targets. Furthermore, a voice message alerts the blind person about the obstacle or known or unknown person. The proposed work aims to create a user-friendly technology for communication of physically liable people which fulfils the basic amenities of the especially abled persons aiming easy-to-use interface, convenience, portability and cost effectiveness. As a result, the proposed approach enables blind users to manage unaware indoor and outdoor locations.
Keywords
Citation
Design and Development of Human Identification and Obstacle Detection System for Blind using Machine Learning. R. Santhiya, K. Praveena Kamal. 2024. IJIRCT, Volume 10, Issue 1. Pages 1-3. https://www.ijirct.org/viewPaper.php?paperId=2311007