基于形态学和SUSAN算子的车牌定位方法  

License Plate Location Method Based on the Morphology and the SUSAN Algorithon

作　　者：郑之[1] 黄键[2] 

机构地区：[1]福建师范大学数学与计算机科学学院,福建福州350108 [2]福建儿童发展职业学院,福建福州350001

出　　处：《福建教育学院学报》2010年第5期109-112,共4页Journal of Fujian Institute of Education

基　　金：福建省教育厅科技计划项目(JA10064)

摘　　要：车牌定位是智能交通管理中车牌识别的重要环节,文章首先对车辆图片进行预处理,先用自适应阈值的SUSAN算法获取车辆边缘,再根据数学形态学去除边缘图片中的噪音点和无关边缘,突出车牌区域的特征,最后根据水平扫描和投影法确定车牌位置。实验证明,该方法能有效定位含噪声点的车牌图片,定位准确。The car plate recognition system is an indispensable part of intelligent traffic system. To being with, the author preconditions the picture of a car by using the Susan algorithm with adaptive threshold in order to detect the plate＇s edge. Then, for the purpose of highlighting the features within the range of that car plate, the noise points and the irrelevant edges are wiped off thoroughly by applying the methods based on mathematical morphology. Finally, the plate is located by using horizontal scan and projection method. The experimental results show that this particular method applied in this paper can effectively detect the pictures of car license plates with noise points.

关 键 词：车牌定位 SUSAN 边缘检测 形态学 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]