基于字符连通域特征的车牌定位方法

车牌定位是整个车牌识别系统的关键技术,传统方法普遍存在实时性差、适应性不强等问题。强调硬件系统构架,固定部分图像输入环境,引入大量先验知识,并最终利用车牌字符连通域的显著特征,将车牌定位与车牌字符的显著性特征相联系,缩短了车牌识别的流程,实现了可适应性强、定位准确的车牌定位。实验结果证实,该算法准确率高,效果明显且具有较好的稳健性。

The License Plate Localization Algorithm Based on Features of Character Connected Component

License Plate Location is the key technology in License Plate Recognition System. Most prevalent traditional methods are poor of real-time and flexible. Thinking of the human visual recognition system, focusing on the use of the salient features of the license plate characters, this paper connects the license plate license plate location with the features of the characters. It shortens the process of license plate recognition system, strengthens the adaptability of the license plate location. At last, the experimental proves that this algorithm is high accuracy and obvious.