HUMAN IDENTIFICATIONAND OBSTACLE DETECTION SYSTEM FOR BLIND

HUMAN IDENTIFICATIONAND OBSTACLE DETECTION SYSTEM FOR BLIND

Ms.B.Narmada1, Mr.R.Madhankumar2,Mr.N.Javeed hussain3,Mr.S.Harish4, Mr.C.S.Hari haran5

1Assistant Professor, Department of Computer Science & Engineering, Dhirajlal Gandhi College of Technology, Salem, Tamilnadu, India

2,3,4,5 UG Scholar, Department of Computer Science & Engineering, Dhirajlal Gandhi College of Technology, Salem, Tamilnadu, India

---------------------------------------------------------------------***---------------------------------------------------------------------

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. Advancements in spatial cognition theory for blind and visually impaired (BVI) individuals have paralleled the rapid evolution of information technology. These breakthroughs have opened up new opportunities, empowering BVI individuals to navigate and interact with the world around them more effectively. Assistive devices, digital mapping systems, virtual reality, and augmented reality have all played significant roles in enhancing spatial cognition for BVI individuals. These advancements have improved their quality of life, fostered independence, and opened doors to education and employment opportunities. As a result, this prototype develops the concept of supplying them with a simple and cost-effective solution via artificial vision. This project presents an AI-based framework that simplifies accessibility for individuals with visual impairments. It aims to benefit both these individuals and society as a whole by leveraging AI technology. The framework offers user-friendly and intuitive solutions, catering to the specific needs of visually impaired individuals, and promotes inclusivity in society. mwe developed an intelligent system for visually impaired people using a Machine learning algorithm, i.e., convolutional neural network architecture, to recognize the human and scene objects or obstacles automatically in real-time. The system accurately recognizes humans in complex environments with multiple moving targets, providing users with complete information on presence and position and nature of the available targets. Furthermore, a voice message alerts the blind person about the obstacle or known or unknown person. The project aims to create user-friendly communication technology for physically disabled individuals, providing an easy-to-use interface and convenience. It focuses on meeting the basic needs of disabled individuals and enhancing accessibility., portability and cost effectiveness The suggested approach empowers visually impaired individuals to effectively navigate both indoor and outdoor environments, even in unfamiliar settings.

Keywords— Spatial cognition theory, convolutional neural network, user-friendly, easy-to-use