Vision-cart: IoT - Enabled Smart Glasses for an Enhanced Shopping Experience
P Poovizhi, Vijaya Kumar T, Rajasekaran P, Priya Dharshini S, M Rithiha, A Dhanushkumaran · 2025
Vision-Cart is a cutting-edge assistive system on smart glasses to improve the shopping experience, with the aim of assisting visually impaired individuals by utilizing advanced AI and computer vision technologies. The goal of this project is to create an AI-based object detection system with which visually impaired individuals can easily move around and identify objects in their surroundings. With a high-resolution camera, the system translates visual data and YOLOv5 enables real-time object detection, identifying individual objects, shelves, and other useful items. These objects are conveyed to the user in real-time audio signals via earphones, making it simpler to interact with the shopping environment. This wearable technology, owing to its simplicity, enables shopping as an independent and accessible process, offering visually impaired consumers greater accessibility, confidence, and independence in daily activities. Compared to existing models such as SSD MobileNet (accuracy of 90%) and Faster R-CNN (accuracy of 96%), the proposed Vision-Cart system utilizing YOLOv5n achieves an overall detection accuracy of 98%, ensuring both reliability and real-time performance. Blind consumers tend to face challenges in identifying products on their own while shopping because of the lack of efficient assistive technologies. This paper resolves the problem through the creation of Vision-Cart, an IoT-based smart glasses platform consisting of a high-resolution camera, YOLOv5n object detection, OCR, and a text-to-speech (TTS) module for real-time product recognition. The platform takes product images, undergoes processing through computer vision algorithms, and provides audio feedback through earphones. The result shows increased accuracy in object recognition and shopping independence, which allows visually impaired users to make their own choices without any outside help.