复杂环境下的车牌定位方法  

License plate locating method in complicated environment

作　　者：赵伟[1] 鞠美玉 邓艳[1] 

机构地区：[1]东北林业大学机电工程学院,黑龙江哈尔滨150040

出　　处：《计算机工程与设计》2016年第4期982-987,共6页Computer Engineering and Design

基　　金：黑龙江省基金支撑基金项目(F200925)

摘　　要：为使车牌定位技术适应复杂环境,给字符识别提供便利条件,提出基于区域放大的车牌定位方法。对图像进行边缘检测,粗定位时采用形态学处理和基于迭代融合的连通域筛选的方法检测车牌初步定位区域,第二次通过多因素决策的方法去除伪车牌,采用区域放大法进行车牌精定位。实验结果表明,该方法准确性高,在工程应用中具有一定的实用价值。To make the license plate location technology adapt to the complex environment and provide more convenient conditions for the further character recognition,a method of license plate localization based on area amplification was presented.After edge detection,rough-locating was implemented for the first time through mathematical morphology and connected domain screening based on iterative fusion to locate the region of license plate coarsely.The method of multifactor decision was used to remove the pseudo license plates for the second time.Accurate location of the license plate was then obtained using the area amplification method presented.Experimental results show that the method has high accuracy and strong timeliness,and it has huge value for practical reasons.

关 键 词：复杂环境 车牌定位 区域放大 连通域筛选 多因素决策 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]