基于灰度跳变与字符间隔模式的车牌定位方法研究

A Method of Car License Plate Location Based on Gray Beep and Char Interval Mode

摘要:

车牌定位是车牌自动识别的第一步,而如何考虑光照影响是车牌定位是否成功的关键;通过深入分析不同的车牌图像,提出一种基于灰度跳变与字符间隔模式的车牌定位方法;首先,针对不同光照条件下采集到的车牌图像明暗度的不同,利用多阈值处理方法得到车牌信息不丢失的、最佳的二值图像,然后,在其二值图像中首先利用灰度跳变定位车牌的上下边界,接着对字符垂直投影后的宽度进行统一的调整并以固定的字符间隔特征定位车牌的左右边界,从而完成车牌定位;最后,通过实验验证了该方法的有效性。

Abstract:

Car license plate location is first step of car license plate auto-recognition,how to consider the light conditions is one of the keys whether or not the car license plate can be located successfully. First,a muti-threshold method was employed to obtain the optimal binaryzation image according to different lighting conditions. Second,gray beep was facilitated to determine upper and lower edges of the car license plate. Third,left and right edges of the car license plate were located and then,the full location of car license plate can be finished. Finally,the proposed method was verified through experiment. 