Plate Number Recognition Using Segmented Method with Artificial Neural Network

This article presents a license plate number recognition system for moving vehicles for Turkish license plates. The proposed system is designed to read information of vehicle plate numbers automatically from digital images for many purposes; such as over-speed control, parking areas, traffic control, and top governmental agencies, etc. The proposed system mainly consists of two stages: the first stages are the recognition process which consists of vehicle detection from license plate number, localizing and plate position estimation, segmentation of words and numbers, and license plate recognition stage. The second one is the use of the neural network; three different types of networks were used. (Pattern net, perceptron, and multi-layer neural network). Simulation result indicated that pattern net has a very good performance in recognizing the license plate image compared to the other two types of networks. Also, has the advantage of less training time compared to other types of neural networks.