License Plate Recognition Technology And Its Applications In Intelligent Transportation Systems

Traffic and communications are two mainstays of the social economy, and especially, traffic problem has been becoming more and more important for our social life. With the development of the social economy and improvement of people's standard of living, traffic load increases at great speed, therefore, the application of intelligent transport system is imperative. As a main part of intelligent transport system (ITS), license plate recognition (LPR) has great application prospective in tolling, monitoring traffic flow, investigating on-the-spot traffic accident, handling breaks of the traffic regulations and keeping parking secure. People pay increasing attention to LPR based on digital image processing and pattern recognition.Using the method of image recognition, considerable analysis and researches on LPR have been done in this paper, which are divided into four components including vehicle license plate location, license plate binarization, isolation of the characters and character recognition. A simple and fast algorithm has been proposed.First, the significance and difficulties of the development and realization of LPR have been introduced;then, after the researches on the existing license plate location based on mathematical morphology, a more suitable method of the vehicle license plate location based on projection method and fuzzy edge detection is employed, this method is more advantageous to locate license plate with eight-direction Sobel operation;next, after analyzing existing approaches of license plate binarization, the problems existed can be found out, and license plate binarization based on Lorentz information measure is adopted. At the same time, license plate geometry correction method is produced. After that, combining with the traditional isolation method of the characters, this paper uses connected component detection and projection method on isolation of the characters, and makes the characters unitary;finally, methods of character feature extraction and recognition especially for figures and letters have been researched.