The positioning of the license plate has an important position in the license plate recognition system, which is a prerequisite for the subsequent character recognition of the license plate. However, because the license plate pictures of the license plate positioning are collected outdoors, the image background is complex, the noise interference is serious, and the image quality is low, so the license plate positioning is often affected and cannot be accurately positioned. Therefore, in the license plate positioning algorithm, the key is to find a certain image processing method, so that the original image can be clearly displayed after the processing of the license plate area, and the non- license plate area in the image disappears or weakens, which can accurately and effectively Locate the position of the license plate in the image. This article mainly focuses on white license plates on a blue background. First, the blue features of the license plate and the image processing method are used for the initial positioning, which reduces the number of candidate areas for the license plate. Then, the license plate image for the initial positioning is projected to complete the positioning of the license plate. 1. Initial positioning of license plate 1.1. License plate after conversion from RGB space to HSI space The color image contains rich color information, giving a good visual effect, and is positioned for the first time according to this characteristic. But in general, the color pictures are under the RGB model, and the HSI model is more suitable for the human visual system. Therefore, color space conversion is required to convert the RGB model to the HSI model. The conversion formula from RGB space to H SI space is : When B <= G, H = θ; when B> G, H = 360 °-θ. In the white license plate with blue background, the hue H of blue is about 240 °, and the saturation S value is larger. Through these two quantities, you can filter the blue part of the input image to remove a lot of background noise. After experimental testing, the color of the blue license plate is> = 0.75, and the saturation is> = 0.51. It can be seen that the range values ​​of the chroma and saturation of the HS I space can be used to obtain the coarsely positioned license plate area, and the results are shown in FIG. 1. 1.2. Pretreatment process of license plate positioning After preliminary positioning, the license plate range is reduced, and the license plate image is processed in grayscale. The texture distribution of the grayscale image is mainly in the car lights, license plates, and radiators, and the grayscale value of the license plate position is also different from other parts. Most gray scale changes in the area are relatively smooth. (1) Remove isolated highlights In general, the process of collecting license plate images is affected by various factors, such as background, lighting and some characteristic factors of the car itself, which is likely to cause noise in the picture. Since the initial positioning has removed most of the background of the license plate picture, it is reduced Noise point. In order to reduce the possible area of ​​the license plate, the bwmorph function in the Matlab toolbox can be used to effectively remove the isolated points. The result is shown in Figure 3. (2) Shift scanning and edge detection Shift scanning is to scan the entire image from left to right, using adjacent pixels as the gray level to weaken the horizontal texture, and retain and increase the gray level at the vertical transition, as shown in equation (4). In the formula, f (xj, yi) is the original image, and g (xj, yi) is the scanned image. After processing, the vertical texture and lines of the image become more obvious, which weakens other areas and highlights the license plate area. As shown in Figure 4. Then using edge detection, the boundary of the area where the license plate is located is highlighted from the whole picture, so that the characteristics of the license plate area are more obvious. The effect is shown in Figure 5. Figure 5 edge detection diagram Fiber Optic Distribution Box,Fiber Optic Breakout Box,Fibre Optic Breakout Box,Fibre Break Out Box Cixi Dani Plastic Products Co.,Ltd , https://www.cxdani.com
