Car License Plate Automatic Identification Technology Research

Vehicles' license plate recognition system(LPRS) is the main part of the contemporary Intelligent Transportation System(ITS), and it can be applied in vehicle management situations of all levels and all kinds. Compared with traditional vehicles managing methods, it improves managing efficiency and level, and saves manpower and material resources, realizes scientific standard management and ensures traffic order. Therefore, it has comprehensive application prospect.LPRS consists of three modules in general, those are: license plate locating, character segmentation and character recognition. The dissertation analyzes and compares with algorithms of all modules related to LPRS deeply and presents my own viewpoint.In license plate locating, it analyzes and compares many license plate locating algorithms, such as direct method, multi-resolution method, mathematical morphology method and method based on color, etc. in addition to, it presents a license plate locating algorithm based on back propagation artificial neural network.In character segmentation, it analyzes and compares a lot of algorithms about license plate image enhancement, binary image and standardization and geometrical revising. Furthermore, it presents adaptive gray level flexing algorithm. And then, a character segmentation method is used to segment character, which is based on projection and pre-known knowledge of the size and the space between characters of characters of vehicle license plate.In character recognition, the dissertation classifies the characters of vehicle license plate to two different regimentations: one is the Chinese characters, the other is the symbols including alphabetic and digital characters. And it firstly analyzes some character recognition algorithms used much at present, such as template matching algorithm, characters features algorithm and artificial neural networkalgorithm. And then it puts forward thoughtway of combination of character recognition algorithm. The material method of the thoughtway is that: the two regimentations use different recognition algorithms. It introduces improved template matching algorithm to recognize the Chinese characters. And about the symbols, after analyzed the structural properties of alphabetic and digital characters on vehicle license plate in detail, the dissertation selects features of minutiae, closed curve and corners in strokes as the foundation of character recognition to recognize characters in license plate.The experiments show that the method proposed by the dissertation can attain a quite finer vehicles license plate recognition effect. Thereinto, the precision rates of Chinese characters, alphabetic and digital characters are 98%, 97.8% and 98.95%, and it achieves practical requirements.