Application Of Image Processing In The License Plate Recognition

As the key technology of realizing intelligent and modernization in traffic system, the license plate recognition (LPR) has attracted more and more attention.In this dissertation, some characteristics are gotten based on automobiles vehicle plate analysis. The key technologies of LPR are researched and discussed based on these characteristics by using the technique of digital image processing. Preprocessing of image, license plate locating, character segmentation and character recognition are mainly expatiated in this paper. After that, the LPR prototype system is developed.After the various integrated experiments of various vehicle images, it has been found out that preprocess of image is more appropriate. These preprocess includes grey, ameliorating median filtering. Through the processing, the noise on the image is eliminated effectively and improved image quality. By studying plate characteristics of the various positioning algorithm comparison and analysis, and summarizes the characteristics of these algorithms, this paper has raised its positioning methods, including the method of rough positioning and precision positioning, which using the combined new method.In analyzing the existing division of several typical methods, a tactic is proposed, which is combined with connection region, projection and static bounds method, achieving accurate locating plates characters. Characters recognition includes Chinese character recognition and alphanumeric identification: the Chinese character recognition by the template matching and character recognition combining matching features improved identification methods. Tally images through mathematical morphology closed operations, such as processing detailed, the images are then processed to extract characters structural characteristics, design simple classification devices directly to identify the characters. This approach is good in speed, rates of identification, can reaching more satisfactory results.The algorithm we adopted is not restricted by the location of the plate in the image, and it has strong anti-jamming ability to lean, distortion, pollution and blur. The algorithm is also adaptable to the varieties of circumstance light and image contrast.