摘要
提出一种基于数学形态学和均值聚类的实时车牌定位算法,将边缘处理与聚类分析相结合,得到车牌字符的垂直边缘信息,然后通过数学形态学运算处理,结合车牌的多个特征对车牌进行定位,试验证明,该算法准确率高,抗干扰性强。
A real-time license plate location algorithm based on mathematical morphology and K-means is proposed. By clustering analysis and sobel operations, the vertical edge information of license plate characters can be acquired. Then by further morphological operations and combining with multi-features of plate, the license plate region can be located. The experiment results show that the algorithm improves the ability of anti-interference and the accuracy of location.
出处
《通信技术》
2008年第12期265-267,共3页
Communications Technology
基金
江西省教育厅科学技术研究项目
赣教技字[GJJ08377]号
关键词
均值聚类
车牌定位
数学形态学
K--mean clustering
license plate location
Mathematical morphology
