License Plate recognition system

Abstract

Many facilities charge per vehicle entry for usage. Such facilities include parking areas, highways, bridges or tunnels. It is common to have staff at the checkpoints to control the payment of fees or to have machines if a set fee is required. The purpose of this research is to investigate a suitable way to read and recognize the registration plate from a photograph of a vehicle. An automated system could then be implemented to control the payment of fees. In fact, any situation requiring the automatic control of identification of a vehicle with a license plate number may be a potential application for such a system. At roads there is a need of a system which can detect stolen cars and also suspicious vehicles for security purposes. This report describes analysis, design and implementation of a system for automatic recognition of license plates, which is considered a subsystem for automatic speed control. The input to the system is a series of color images of moving vehicles, and output consists of the registration number of the license plate. Extraction of the desired information is done in three steps. First, the license plate is extracted from the original image, then the characters are isolated, and finally each character is identified using statistical pattern recognition and correlation. The algorithms were developed using a set of training images, and tested on images taken under varying conditions. The final program is capable of extracting the desired information in a high percentage of the test images.