基于彩色二值化的车牌定位方法

提出了一种基于彩色二值化的车牌定位方法。首先将彩色图像从RGB颜色空间转换到HSI颜色空间,同时生成一个与彩色图像大小相同的二值化状态特征矩阵,根据车牌的色彩特征,调整状态特征矩阵;再用数学形态学方法对状态特征矩阵进行填充空洞和滤除噪声的处理,并根据车牌的几何特征除去伪牌照区。该方法将图像的色彩特征与状态特征分离,充分利用车牌的色彩特征调整彩色图像的状态特征,并融合了数学形态学方法;而且将车牌的色彩特征和几何特征进行了有机的结合。实验结果表明该方法是一种有效的车牌定位方法。

Vehicle License Plate Locating Based on Binary Color Image

A new approach for locating vehicle license plate based on binary color image is proposed.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 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.In the proposed method,color features and state features are separated from each other and color features of the plate are adequately used to adjust the corresponding state features.And color features and geometrical features of the plate are combined.The experimental result shows that the approach is good for vehicle license plate locating.