Blind People Assistance for Object Detection Using AI

Abstract

Assisting visually impaired individuals in object detection and recognition using artificial intelligence has emerged as a promising research area. In this project, we propose a blind people assistance system that uses the YOLO (You Only Look Once) algorithm to detect objects in real-time and provide audio feedback to the user. The YOLO algorithm is known for its high accuracy and fast processing speed. Our approach involves training a YOLOv3 model on a dataset of labeled images that includes objects commonly encountered in daily life, such as chairs, tables, and doors. Once the model is trained, it is integrated with a text-to-speech engine that provides audio feedback to the blind user by announcing the object class and location in the image. The system can be an effective tool for enhancing the independence and mobility of visually impaired individuals. Our project demonstrates the potential of using AI to assist blind people with object detection and recognition, and we believe that our approach can make a significant contribution to improving the lives of individuals with visual impairments.