Computer Vision is a branch of Artificial Intelligence that specializes in obtaining valuable information from digital images and videos. With rapid advancements in deep learning techniques, deep convolutional neural networks (DCNNs) have become more important for object detection and image processing, fundamental tasks in computer vision. These object detection systems accurately capture and identify many objects of predefined categories from the given image. This study explores the application of computer vision and deep learning techniques to automate shelf analysis in the retail and FMCG (Fast-Moving Consumer Goods) sectors. This paper introduces a You Only Look Once (YOLO) based object detection for supermarkets for easing the transaction and enhancing customer satisfaction. The proposed system framework utilizes YOLOv5 as primary detection algorithm on this dataset and achieved an impressive 100% true negative for background detection and a 65% true positive rate for product detection, with high precision (92.4%), recall (93%), and an F1 score of 88%. These results indicate the model’s robustness in real-world settings. This paper showcases the potential of advanced deep learning techniques in retail and FMCG sectors for accurate and efficient product detection. It can act as a foundation for future applications, including IoT integration to support inventory management, sales tracking, and improved product accessibility, thus bridging gaps between FMCG companies, retailers, and customers in a streamlined and efficient manner.