The result of an increasing number of vehicles that come out of the population gives rise to various social problems, such as traffic infringement, auto theft, and parking issues. Meanwhile, there is a growing demand for enhanced security and inspection point operations with the current systems. We can address such issues by integrating Automatic Number Plate Recognition in the Check Post Management System (CPMS). This transformation is now feasible through the integration of machine learning algorithms. This paper aims to propose a new approach not only to deal with security problems but also to simplify some operational processes. The proposed system uses the YOLO (You Only Look Once) model. It is a deep learning technique based on convolutional neural networks (CNNs). The YOLO model operates on the pictures taken by the camera, giving priority to objects within their diverse attributes, and separating them from the background. It then uses this acquired information to further recognize specific information. For example, a number plate with which we can get the details of the vehicle, driver, and passenger. The recommended system exhibited promising results as the accuracy rate achieved at 87% during the training increased to 90% accuracy in the recognition of the number plates during testing. These findings show the YOLO model's capability to enhance security and operational efficiency at check posts by effectively processing real-time information from images.