Research Of License Plate Recognition Technology

License plate recognition technology has been more and more important with great application fields in our life. Location, character segmentation and character recognition of vehicle license plates are three key steps of license plate recognition. License plate recognition technology is studied in the thesis from the three steps. The main contributions of this thesis are as follows:1. A layered location approach for vehicle license plate and a new approach for locating vehicle license plate based on binary color image are proposed respectively.In the former approach, based on gary image, the layered gradation segmentation is adopted and the analysis range is diminished gradually in the image. The right-and-left and down-and-left boundaries of plate region candidates are located and a few plate region candidates could be obtained. And then the plate region will be selected from them. So the exact location of the vehicle license plate is carried out. The experimental results show that the approach is excellent in the accuracy with a rapid speed and is great in the robustness.The latter is an approach for locating vehicle license plate based on color image. Firstly, the color image in RGB color format is converted to HSI color format, and a binary state feature matrix about the color image is brought up which has the same size as the color image. The state feature matrix is adjusted according to color features of the plate region in HSI color format. Secondly, mathematical morphology is used for processing the state feature matrix so that its holes are filled and its noises are erased. And then the false regions will be eliminated according to the geometrical features of the plate region. In the proposed method, color features and state features are separated from each other and color features of the plate region are adequately used to adjust the corresponding state features. And color features and geometrical features of the plate region are combined in the paper. The experimental result shows that the approach is a good approach for vehicle license plate locating.2. According to the rules of the characters of a vehicle license plate and the geometrical features of the characters, an approach for character segmentation of vehicle license plates is proposed which is based on the location of the third character. Firstly, the third character of the plate is located in the image of the plate location. And then the character regions will be divided and merged. And consequently, character regions will be expanded for lack of a few character regions. Finally, the height of all character regions will be adjusted. As a result, the characters of the plate are segmented accurately. The experimental result shows that this approach is a good approach for character segmentation of vehicle license plate, which can be accomplished with a grate result in a short time.3. Support Vector Machine (SVM) is used to recognize the characters of vehicle license plates in the thesis. According to the arrayed feature of the plates, four types of classifying systems, including Chinese characters classifying system, letter classifying system, figure & letter classifying system, figure 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. 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 figure & letter classifying system; the fifth, sixth and seventh characters are recognized by figure classifying system. The characters of the license are recognized bycombination of the above results. The experimental result shows high recognition rate and fast speed for all characters of a vehicle license plate.