Published Paper Details:

Blindness is a form of disability or inability to see. Lack of vision is only a disadvantage if the activity being pursued by the person who is blind is one that requires sight. Blind people may face troubles only due to inaccessible infrastructure and social challenges. Navigating around places and using pedestrian access signs are one of the biggest challenges for a blind person, especially the one with zero vision. For a physically challenged person, gaining independence may the most valuable asset and a person with visual impairment can lead an independent life in an environment which is designed with required adaptations for them. This paper presents a real-time object detection system using YOLO (You Only Look Once) based deep learning algorithm to help visually impaired people in their daily life. A Cobotic Spectacle is a cutting-edge product designed specifically for visually impaired individuals. The system seamlessly integrates face motion recognition, object identification and text detection functionalities using YOLO Algorithm. YOLO uses convolution neural networks (CNN) and single forward propagation through a neural network for object-detection in real-time. In this proposed system, YOLOv8, a real-time Object detection algorithm trained on the Common Object in Context (COCO) dataset is used to identify the object present before the person which produce high rate of accuracy in object identification. The system delivers the output through synthesized voice, enhancing visual perception. The face motion recognition module promotes improved social interaction, while object identification increases environmental awareness. This integrated solution combines edge processing and cloud-based analysis for portability, real-time processing, and computational efficiency. A Cobotic Spectacle empowers visually impaired individuals, providing a state-of-the-art smart spectacle system that enhances visual perception, promotes independence, and improves their overall quality of life.