Object detection is a very sophisticated technology to work on nowadays. In this study, we specifically focused on solving the problem of license plate detection and license plate class identification for authentication. For both, we used the You Only Look Once (YOLO) algorithm to solve these problems. For the license plate detection model here we used YOLO-v4 and for the number plate, the class identification model used YOLO-v5. The Dataset used in license plate detection is Google’s Open Image Dataset to get YOLO formatted labeled images. And for the Automatic Number Plate Authentication (ANPA) model, we have created a dataset by labeling the images. This concatenation approach is used to solve the problem, first detecting the license plate and extracting the license plate region from the image and then passing this image to the number plate class detection model to extract the information from the license plate image. The concatenation method shows a very good output for both of the models. For the license plate detection model, the mean average precision is 88.57% and our YOLO-v5 model has an accuracy around (a mean average precision) of 95.41%.