Research On Some Key Techniques Of Vehicle License Plate Recognition

With the development of the road transportation, the traditional transportation management by hand can not meet the practical demands nowadays. More and more attention is being paid to the application of telecommunication and computer technologies in transportation and thus it is developing faster and faster. The transportation in China is going into an information and digital era.Being a special computer vision system, the Vehicle License Plate Recognition (VLPR) System can capture a vehicle image automatically and identify the vehicle license plate (VLP) in the image. It may be used in the road tolling system, access control system, stolen vehicle identification system and intelligent transportation system and so on, contributing a lot to the automation of the transportation management.The VLPR system involves the techniques of digital image processing, computer vision, pattern recognition and artificial intelligence and so on. Its key techniques include the VLP location, character segmentation and character recognition and so on. Typical difficulties in the VLPR are the unconstrained illumination conditions, irregular background and the unknown position, orientation and size of the characters.The VLP location, which is to locate the VLP from a vehicle image, is the base of the VLPR. A VLP location algorithm based on the characteristics of the VLP is employed in order to overcome the typical difficulties in realizing the VLPR system. There are three major steps, which are image pre-processing, VLP search and VLP location. The experimental results show that this algorithm is efficient in locating the VLP while not sensitive to the unconstrained illumination conditions and irregular background.The VLP image, which is segmented by the VLP location, must be segmented into several images. Each one includes one character respectively. A connectivitybased character segmentation algorithm, rather than a projection-based one, is proposed and some elementary results are given.The VLP image and some related information can be stored in the VLP database, which is convenient for information query and image display. The database table in this VLP database is made by the Microsoft Access and the database is accessed by the DAO which is provided by the MFC of VC 5.0. The function of addition, deletion, query and image display can be realized by this database.