一种实用新型蓝底白字车牌定位方法及实现

New useful way and its realization for blue background white characters car license plate location

本文给出一种对不同牌照有一定适应性的初始阈值,然后使用Ostu(最大类间方差法)算法确定二值化最佳阈值,为削弱背景及背景噪声的干扰,本文对二值化图像进行数学形态学腐蚀运算,作相邻像素灰度值相减,并使用自定义模板进行中值滤波,最后利用投影法检测出车牌的位置。理论分析及实验结果表明该方法非常有效。

This paper introduces the incipient threshold which is adaptive for different car license plates, then using Ostu algorithm to confirm the best threshold for binarization. To weaken the background noise, this paper applies mathematical morphology cauterization for the binary image, and subtract the pixel, and then filter the image using mid-filter by user-defined template. The paper use the way of projection to detect the location of the car license plate. Both the academic analysis and experiment result prove that it is very effective.