The Research Of Technology In License Plate Recognition

With the high-speed development of our national economy, there are more andmore constructions in the domestic expressway, urban road, and parking area, etc. Therequisition on the traffic control, safety management improves day by day. Theintelligent transportation system (ITS) has already become the main direction ofpresent traffic administration development, and vehicle license plate recognition (LPR)system as core of ITS, plays a very important role. It occupies important status in theproject management of expressway, urban road and parking area, etc. Its wideapplication will contribute to the process of the traffic mechanography of our country.The License Plate Recognition System is composed of license plate detection,plate characters segmentation and characters recognition. The LPR system involvesnumerous discipline domains, such as Pattern recognition and Artificial Intelligence,Computer Vision, Digital Image Processing, Artificial Neural Network etc.Locate the plate is the first step of the LPR system. Its accuracy directly affectsthe success of the character recognition result. Firstly, images pretreation is processed,secondly, mathematic morphology is adopted as the headmost location method, andfinally; horizontal projection based on transcendent knowledge of plate is adopted asthe ultima location method. The result proved that it can satisfy the demand inaccuracy, but not perfect in the speed.The result of character segmentation affects the recognition directly, firstly, aline-scanning method based on transcendent knowledge of plate to is taken to wipe offthe flames, then, binarization and slant-correction are processed, finally, a strategyintegrated connected regions with template matching is adopted to segment thecharacters, it's proved improving the accuracy of segmentation.The method of character recognition takes an important part in the whole system,it has direct effect on the last license plate recognition result. The key technique lies infeature extraction. Typical difficulties are the character blur, character destruction andcharacter image stained because of the performance of the vidicons, the clean degree, illumination conditions and the movement of the vehicle and so on. A assembledmethod is adopted to recognize Chinese characters and other characters separately, agood license plate recognition result is achieved through this method.