The Technology Research Of License Plate Location And Character Segmentation Based On Geometry

License plate recognition technology is an important part of an intelligent transportation system, widely used in highway tolls, unregistered vehicle monitoring, vehicle parking management, and other important occasions. Due to many of the existing algorithms for the system, because of the need to adapt to all kinds of complicated backgrounds, various types of vehicles to identify, changing colors, and the ability to adapt to weather changes caused by different illumination conditions, the current system has some problems. Automatic license plate recognition (LPR) play an important role in numerous applications and a number of techniques have been proposed. However, most of them worked under restricted conditions, such as fixed illumination, limited vehicle speed, designated routes, and stationary backgrounds.License Plate Recognition system includes:pre-treatment, the license plate location, character segmentation and character recognition.As now the character recognition is very mature, the key impact lies in the plate recognition license is plate location and character segmentation. Designed license plate recognition technology on the basis of previous studies, the design proposes one method based on geometric features, License Plate Recognition System this article focuses on three key areas:the license plate image preprocessing, license plate location, character segmentation, and made a thorough research work. Details are as follows:License plate image preprocessing part, captured under a color image into a grayscale image, select the image histogram equalization fix the situation, improve the brightness and contrast of different images and a variety of practical operation.Summing up the de-noisng performance of various operators and combining the noise’s feature affected the plate area and then select the license plate image de-noising median filtering, to get a clearer picture. Finally,it uses the swell and corrosion methods of mathematical morphology to preprocess the license plate, paving for obtaining the rectangle area of the license plate. Some common edge detection operators compared with the image edge detection methods, the continuity is better, so as to follow the edge of the image to locate the license plate of the foundation.Design license plate location in license plate location is proposed based on mathematical morphology and projection methods.Firstly, Utilizing the geometry of the plate’s rectangular structure and the centriod to define rectangular location. Secondly, using the square of the rectangular structure’s perimeter is twenty-seven times more than the square of the rectangular structure’s area. With these two geometric features to achieve the plate’s accurate positioning.In character segmentation part, it study image binary of the license plate. according to the geometry of the large space between the plate characters, no character adhesions, and the fixed length between each character can be set threshold, to obtain accurate segmentation of the plate characters. Finally, to achieve the character size normalized output standard character subgraph. The experimental results show that this method can effectively segment the license plate characters.