Real-Time Medicine Packet Recognition System in Dispensing Medicines using YOLOV8

Dispensing medicine to elderly residents is a crucial task in nursing homes, requiring specialized medical staff to prevent errors and manage inventory. With rapid advancements in deep learning technology, high-performance computers can replace some supervision tasks. In this paper, we have proposed a system consisting of a Convolutional Neural Network- YOLOV8 custom-trained image recognition model, Optical Character Recognition (OCR), and RoBERTa, a pre-trained Large Language Model (LLM) that uses the architecture of the transformer, and it has attained cutting-edge performance on a variety of natural language processing tasks. The RoBERTa model is particularly effective in handling unstructured text data, making it an ideal choice for this project. The model is hosted on a virtual machine instance on the Google Cloud Platform, a cloud computing service that provides a range of tools and services for building, deploying, and managing applications and services. The use of the Google Cloud Platform ensures that the system is scalable, reliable, and accessible from anywhere at any time, making it an ideal choice for a method for recognising pharmaceutical packets in real time