Automatic License Plate Recognition System Research And Development

Nowadays, intelligent transport system (ITS) has become the central aspect to development of traffic department. Automatic identification technology is the focus of ITS, and be regard as one of the important scientific research of traffic department.Research on vehicles' license plate recognition system (LPRS) involves techniques such as digital image process, computer vision, pattern recognition and artificial intelligence etc. LPRS plays an important role in intelligent traffic control system, and it can be applied in vehicle management in situations of all levels and all kinds.LPRS consists of three modules in general, those are: license plate location, character segmentation and character recognition. Algorithms of all modules related to LPRS is deeply studied and analyzed in this paper. And, in this paper finally settle down a series of algorithms used in LPRS based on our research.Our processing objects are close color image snatching by YTZPX system named rush red light cars automatism snatching system. The task is to accomplish plate location, characters division and characters recognition. The whole system includes the next five sections: The design of the video collection and transfers system, image preprocessing module, plate positioning module, characters division module and characters recognition module.Video collection and transfers system is base on ARM processor and embed linux to improve on YTZPX system named rush red light cars automatism snatching system .And aimed to reduce cost and enhance performance of the system.In image preprocessing module, according to the characteristics of the image snatching from YTZPX system, we put forward appropriate preprocessing algorithm to remove or weaken the effect come from weather or ray.In license plate locating module, according to the texture characteristics of license plate, introducing horizontal difference to eliminate disturb come from vehicle itself and image background. So as to outstand plumb edge of license plate.In characters division module, to those canonical images after reprocessing, adopting plumb histogram, to those nonstandard images after reprocessing, we discussed about fragmented character and overlapped character, mentioned the correlative manage ways.In characters recognition module, in virtue of the nerve network have outstanding capability to classify, so in this paper adopt BP nerve network to identify characters.