摘要
研究了ITS系统中最基础、最重要的车牌定位技术。在已有的车牌定位理论和方法的基础上,提出了一种先使用数学形态学搜索车牌候选区域,然后根据车牌的长宽比和面积等特征对车牌候选区域筛选,最后统计二值图像中黑、白像素变化规律实现车牌精确定位的新方法。实验的结果表明,该方法能够有效地定位车牌区域,定位成功率达到91.3%具有较高的实用性。
Researches have done on the technical of license plate localization,which is the most important point in ITS.On the study of traditional theories and methods of license plate localization,this paper presented a new method,it used mathematical morphology to obtain the candidate regions at first,and then license plate＇s feature such as aspect ratio,area were used to filter these regions,at last,the accurate license plate location was determined by the black and white variation of the pixels.The results showed that this method was effective and had an accurate location rate of 91.3%.
出处
《微计算机信息》
2011年第8期124-126,共3页
Control & Automation
关键词
车牌定位
智能交通系统
图像特征
license plate localization
Intelligent Traffic System
image feature
