基于水平垂直灰度开运算的车牌字符分割算法

摘要

采用Hough变换检测车牌的倾斜角度进行车牌的矫正.提出了一种基于水平垂直结构元素开运算的数学形态学方法,对字符分割前的车牌进行预处理.该方法能够在车牌定位不精确的情况下有效地去除车牌边框、铆钉及其他噪声,消除干扰突出字符.运用传统的投影法以及车牌的先验知识进行字符间的分割,有效地提高了字符分割的效果.实验结果证明,该方法有效可行.%Detecting the tilt angle of license plates by the Hough transformation and correcting the license plates. Then, a mathematical morphology algorithm is proposed, which is based on the horizontal and vertical structure element opening operation and used to process license plate images before cutting characters. This way can remove the border and rivets and outstand the characters effectively when license plate is positioned inaccurately. The effect of character segmentation is better by the traditional projection method and the priori knowledge of license ptate. Experimental results demonstrate that this method is effective and feasible.