中文摘要：

目的 车牌定位是车牌识别的关键步骤之一,为提高车牌定位的准确率和定位速度,降低误检率,提出一种基于多信息融合的快速车牌定位方法.方法 首先,通过边缘密度信息快速排除大量背景区域,有效提高定位速度;其次,根据车牌字符的分布信息精确定位车牌;最后使用基于模板匹配的车牌字符分割方法进行车牌字符分割,通过验证所分割出的字符是否是数字或字母来验证所定位区域是否车牌,去除误检车牌区域.结果 在9980幅图像上进行测试,定位准确率为97.9％,平均定位时间为16.3 ms.实验结果表明,本文方法可以在各种条件下快速而准确地定位车牌.结论 融合多种特征的车牌定位方法,通过提取车牌对应的环境信息,排除了大量的背景区域,加快了车牌定位的速度;根据车牌的结构信息定位车牌,并通过车牌的部件信息,实现合法性验证,提高车牌定位的准确率.通过多种信息的融合,有效改善了车牌定位的效果.

英文摘要：

Objective License plate recognition （LPR） is the core module of an intelligent transportation system. LPR algo- rithms are generally composed of the following three processing steps ： 1 ） detection of the license plate region ; 2） segmen- tation of the plate characters ; 3 ） recognition of each character. License plate detection is the key step of LPR, and its result directly determines the performance of the LPR system. Most of current license plate detection methods employ single fea- tures, such as the edge feature, the structure feature or the color feature, to locate the license plate, and cannot obtain sat- isfactory results. In order to improve the accuracy and speed of the license plate detection, and to reduce the false detection rate, we propose a license plate detection method based on multiple features. Method First, edge density information is used to remove most of the background area, which can greatly improve the speed of the detection process. We divide the image into small cells, compute the edge density of each cell, and remove the cells whose edge density are too large or too small. Then we use the distribution information of the license plate characters to precisely detect license plates in the remai- ning regions. Coupled morphological operators are used to employe the character regions and Hough transformation is used to obtain the position of the license plate. After that, we segment the license plate into characters and get the Histogram of Gradient （HOG） features of each character. The HOG features of each character are used to verify whether the character is a rightful license plate character （letter or digit） . If there are more than five rightful characters in the license plate candi- date, the candidate is regarded as a true plate. Result We establish a dataset that contains 9 980 high-resolution images, and test our algorithm in three ways, that is, detect license plate by 1 ） context and structure information, 2） structure andpart information, 3 ） context,