Arabic-Numbers Recognition System for Car Plates

In the modern era, computers are used to automate most of the operations used to be done by humans. This leads to higher performance and low cost of operations. The field of traffic management is not an exception. In this paper, we propose an automatic license plate recognition system which can extract the license plate number of the vehicles using machine learning models and image processing algorithms. License plate recognition systems pass through three successive stages and differ in the techniques used to achieve the output. In this paper, Locating the license plate in a given image is the first stage. It is achieved using Faster Region-Based Convolutional Neural Network, which is capable of identifying regions with objects based on regions proposal network. It is also capable of classifying the detected objects. Second stage is the segmentation of the plate using image processing algorithms and final stage is to recognize the segmented digits using convolutional neural network model. Results reveal that the presented system successfully detects and recognizes the vehicle number plate on real images, achieving an overall accuracy of 93% with a total of 100 images.