The Research On Vehicle License Plate Location Algorithm

The thesis mainly carried on researching for vehicle license plate location algorithms in the process of the Vehicle License Plate Recognition, which is mostly applied in the scenes such as freeway charge gate and resident garage management.Automatic Vehicle Identification is mainly composed of three key technologies, namely, vehicle license plate location, character segmentation and character recognition. Furthermore vehicle license plate location is more important key among the best, for location results will directly influence the correction ratio and recognition time of eventual character recognition.However, there are so many difficulties in the vehicle license location, as new styles of cars, various figuration, sheltered boundaries of license plate and indistinct gray difference, and so on .So the research for the vehicle license plate algorithm is still the hot project in the fields of academe these days.Primary researches on vehicle license plate location algorithm completed and realized in the thesis as followed.First, all kinds of location methods from other documents are systematically analyzed, and some key problems on vehicle license plate location are summed up.Second, section thinking is applied in the process of vehicle license plate rough location, which greatly simplified the process of license plate locationThird, on the base of rough location above mentioned, vehicle license plate exact location is completed by means of the combination of threshold segmentation and normal distribution, and then the right and left boundaries are segmented one by one ,by making good use of some properties of character itselfNext, rough location of car license plate and character segmentation are merged together into integrated unit. Rough location results are directly regards as the input images of character segmentation, and then carried on pre-proceeding by Logical Level Technique. The method can distinctly shorten the whole system run-time.At last, a great deal of experiments are done to contrast the methods presented in the thesiswith former ones from documents ,and the experimental results are objectively analyzedThe results show that these algorithms above mentioned both gave prominence to the way of run- speed To five hundred images at hand, on the Penlll personal computer with memory capacity of 256M, rough location holds 10ms, and both rough and exact location only hold 40ms, and the location rate is close to 90%.