一种基于边缘信息的车牌字符分割算法

Vehicle License Character Segmentation Algorithm Based on the Edge Information

提出了一种新型的基于边缘信息的车牌字符分割方法,首先对采集的彩色车牌进行灰度化,在去除噪声后,对车牌区域利用SUSAN算子进行边缘检测.通过垂直投影分割,确定字符区域的不同宽度,利用字符宽度的分类与区域前后文宽度的变化可降低误分割的概率.实验结果表明,采用该算法对车牌字符进行分割时,可显著提高分割的正确性.

A license plate character segmentation algorithm based on edge information is pro- posed. First, what is applied to the colored license plate is the image graying, which is fol- lowed by de-noising. Then, the edge detection based on SUSAN operator is conducted. By ver- tical projection segmentation, the widths of the characters are determined, hence, the differing types of character areas, each of which is treated accordingly. Experimental result shows that this algorithm is effective in segmenting the vehicle license plate characters