【摘要】 采用中值滤波、边缘检测、二值化等方法对车牌图像进行了预处理,并将车牌区域每行的边缘点数量、边缘点数量与车牌区域长度的比值及各候选区域的长宽比等因素作为参考值分别对车牌进行了粗定位和精确定位,利用统计特征和结构特征相结合的方法对字符进行了分类与识别,设计了字符分类器。实验结果表明,所设计的车辆车牌自动识别系统较好地实现了不同环境条件下的车牌识别,识别率达92%。更多还原

【Abstract】 The number of edge points,the length of license plate area and the number of each line of edge points are used for localization.Statistical character method combined with structure character method is applied to obtain the characters and character classifier is designed.Experiment shows that the vehicle license plate recognition system designed in this study realizes that the recognition accuracy rate is up to 92% in various environmental conditions.更多还原