交通车辆车牌运行图像字符自动监测  

Traffic Vehicle License Plate Running Image Character Automatic Monitoring

作　　者：杨英仓 杨晨 

机构地区：[1]贵州警察学院刑事技术系,贵州贵阳550005 [2]贵州省道路交通事故鉴定工程技术研究中心,贵州贵阳550005 [3]贵州大学大数据与信息工程学院,贵州贵阳550025

出　　处：《计算机仿真》2018年第2期384-387,416,共5页Computer Simulation

基　　金：贵州省道路交通事故鉴定工程技术研究中心开放基金(黔道交鉴合G字[2015]10012);贵州省科技厅社会攻关项目(黔科合G字[2014]4001号)

摘　　要：对交通车辆车牌的运行图像字符的自动监测,能够有效解决摄像头拍摄车牌图像质量低、模糊等问题。对交通车辆车牌图像字符的识别监测,需要对车牌运行图像进行灰度化处理,通过寻找交通车辆车牌的优割字符,完成车牌图像字符的自动监测,传统方法对车牌间隔特征进行特征筛选,剔除交通车辆车牌运行图像复杂边框,但忽略了寻找交通车辆车牌的优割字符,导致识别监测精度偏低。提出基于线状中值滤波的交通车辆车牌运行图像字符自动分割识别方法。采用线状中值滤波对采集的车辆车牌运行图像进行平滑处理,提取出交通车辆图像的边缘,对交通车辆车牌图像进行模糊判别,对交通车辆车牌图像进行灰度化处理,通过寻找交通车辆车牌的优割字符对车牌区域进行分割,由此完成交通车辆车牌图像字符识别。实验结果表明,所提方法具有分割速度快、识别能力强的优点。This article proposes a recognition method for automatic segmentation of image characters in running of vehicle license plate. Firstly, the running image of vehicle license plate collected by using linear median filter is smoothed, and then edge of traffic vehicle image is extracted to fuzzily judge license plate image of traffic vehicle and processed license plate image of traffic vehicle with gray level. Finally, by searching for the preferably segmented characters of vehicle license plate, license plate region is segmented. Thus, the character recognition of license plate image of traffic vehicle is completed. The experimental results show that the proposed method has fast segmentation and good recognition ability.

关 键 词：交通车辆车牌 运行图像 字符自动监测 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]