一种改进Radon变换的车牌图像识别

发布时间：2018-01-25 16:57

本文关键词： 模式识别车牌识别倾斜校正图像处理　出处：《广东技术师范学院学报》2016年11期 　论文类型：期刊论文

【摘要】：随着物联网技术在交通运输领域的应用,以及人们对交通管理的要求越来越高,智能交通管理已成为了研究热点之一.而车牌识别技术(Vehicle License Plate Recognition,VLPR)是智能交通系统的重要环节,是视频图像识别技术在汽车牌照识别中的应用.车牌识别技术可以将运动中的汽车牌照从各种复杂环境中提取并识别出来,能够识别车辆牌号、颜色等信息.车牌识别技术在交通运输中的应用越来越明显,具有很大的研究价值.论文中利用图像处理技术对车牌图像进行处理,准确定位车牌区域,然后对由于运动等原因所造成的车牌倾斜进行Radon变换校正,实现了对车牌的字符进行分割和识别,倾斜车牌识别率为90%,经过校正后的识别率可达98%,达到了良好的效果.
[Abstract]:With the application of Internet of things technology in the field of transportation, and people's demand for traffic management is becoming higher and higher. Intelligent traffic management has become one of the research hotspots, and license plate recognition technology is vehicle License Plate Recognition. VLPRs is an important part of Intelligent Transportation system (its). It is the application of the video image recognition technology in the vehicle license plate recognition. The license plate recognition technology can extract and recognize the moving vehicle license plate from various complex environments, and can recognize the vehicle license plate number. Color and other information. License plate recognition technology in traffic and transportation is becoming more and more obvious, which has great research value. In this paper, image processing technology is used to process the license plate image and locate the license plate area accurately. Then the license plate tilt caused by motion is corrected by Radon transform, and the character of license plate is segmented and recognized. The recognition rate of tilted license plate is 90%. After correction, the recognition rate can reach 98%, and the result is good.
【作者单位】：广东技术师范学院计算机科学学院;
【基金】：广东省科技计划工业高新技术领域攻关项目(No.2013B010401032)
【分类号】：TP391.41
【正文快照】： 0引言随着人们生活水平的不断提高,城市中的汽车数量迅速增长,使得由于管理不科学所造成的交通问题日益突出,如何更加智能地管理交通成为了人们关注的热点.现有的高速公路事故自动检测、社区车辆管理等系统.这些系统都是通过传感器对运动中的汽车进行检测,获得相关的数据,以实

【相似文献】