Artificial Intelligence Based Shopping Cart Designed on Neural Network and Mobilenetv2 Framework

This paper presents an AI-powered self- checkout system, iCheckout, designed to improve the retail shopping experience by integrating machine learning, computer vision, and edge computing. The system employs MobileNetV2 for product identification and an HX711-based load cell weight sensor for verification, ensuring high accuracy and efficiency. Unlike traditional barcode-based checkouts, iCheckout eliminates the need for human intervention, offering a seamless and contactless transaction process. Experimental results demonstrate a 90% object detection accuracy and a 74% precision rate for weight verification, with optimized edge processing to reduce latency. The system is designed for scalability and cost-effectiveness, making it a practical solution for smart retail automation.