基于HALCON的车牌识别技术研究  

Study on License Plate Recognition Based on HALCON

作　　者：林辉[1] 蔡秉华 张艺彬 蔡嘉安 许文强 曾台政 LIN Hui;CAI Binghua;ZHANG Yibing;CAI Jiaan;XU Wenqiang;ZENG Taizheng(Shaoguan University,School of Physics and Mechatronics Engineering,Shaoguan,Guangdong 512005,China)

机构地区：[1]韶关学院物理与机电工程学院

出　　处：《机电工程技术》2019年第11期8-10,201,共4页Mechanical & Electrical Engineering Technology

基　　金：广东省教育厅青年创新人才类项目（编号：2015KQNCX147）

摘　　要：结合机器视觉与计算机技术对车牌识别技术进行研究,以HALCON机器视觉软件为核心,采用局部阈值法根据车牌的形状特征对车牌进行定位;其次使用模板匹配对连通域的字符与车牌图像字符进行匹配,解决了汉字字符不连通的问题;最后采用多层感知器的OCR分类器对字符进行识别。实验结果表明,所提出的车牌识别方法成功率达90%以上,具有一定的实用价值。Combined with machine vision and computer technology,the license plate recognition technology was studied.Based on the HALCON machine vision software,the local threshold method was used to locate the license plate according to the shape characteristics.The template was used to match the character and license plate image of the connected domain solving the problem that the Chinese characters are not connected.The OCR classifier of the multi-layer perceptron was used to identify the characters.The experimental results show that the success rate of the license plate recognition method proposed is more than 90%,which has certain practical value.

关 键 词：机器视觉 HALCON 车牌定位 字符识别 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置]