The Research And Implementation Of Vehicle License Plate Characters Recognition Technology

With the development of national economy, the amount of kinds of vehicles has increased rapidly, which not only made in deed our life convenient but also cause a lot of problems. The importance of ITS (intelligent transportation system) is obviously. In addition, vehicle license plates automatic recognition technique is the kernel of ITS. And accuracy and speed of recognition of characters are key index of this kind of technique.The thesis makes systemic research on two steps included in the algorithm. They are character segmentation and character recognition.For the character segmentation, depending on the traditional vertical projective segmentation and the transcendental width and height knowledge of every character in the vehicle license plates, we propose a character vertical projective segmentation method based on transcendental knowledge of every character in the plates. This method achieves a good performance in correcting errors and eliminating interference.Support Vector Machine (SVM) is used to recognize the characters of vehicle license plates in the thesis. According to the arrayed feature in the plates, four types of classifying systems, including Chinese characters classifying system, letter classifying system, letter & numeral classifying system, numeral classifying system, are configured. Every character in a vehicle license plate will be recognized by the corresponding classifying system according to its sequence number in the plate by LIBSVM . The first character is recognized by the Chinese characters classifying system; the second character is recognized by the letter classifying system; the third and fourth characters are recognized by letter & numeral classifying system; the fifth, sixth and seventh characters are recognized by figure classifying system. The characters of the license are recognized by combination of the above results. The experimental result shows high recognition rate and fast speed for all characters of a vehicle license plate.To accomplish real time successfully, it gives the total solution of the embedded system design. The hardware of this system is based on Samsung StrongARM. S3C2410 processor and the software are based on embedded Linux. It is developed under GNU open source software tools (GCC and its cross-compiler, toolchain). The research in this article shows that the total solution of the license plate recognition system design can satisfy the Real-time,exact and feasibility.