摘要
汽车车牌区域定位时受到外界复杂环境干扰常导致定位率降低,为了有效解决此问题,提出了一种直线检测并配合数学形态学的方法对车牌区域进行定位。首先对车牌图像进行了图像预处理,然后利用直线检测模板对矩形的车牌区域进行滤波处理,检测出车牌垂直和水平两个方向的直线边缘从而实现车牌的精确定位。实验结果表明,在保证精度的同时,提高了车牌定位的速度,可以快速准确地定位出车牌。
In order to solve the problem that the locality rate is low due to the interference of the external environment,a method of straight line detection and mathematical morphology to detect the license plate area is proposed. Firstly,the image preprocessing is carried out on the license plate image,and then the license plate area of the known angle is filtered by the straight line detection template to detect the straight edge of the vertical and horizontal directions of the license plate to realize the precise positioning of the license plate. The experimental results show that,while ensuring the accuracy of the license plate to improve the positioning speed,the license plate can be quickly and accurately located.
作者
蔡秀梅
周川力
CAI Xiumei;ZHOU Chuanli(School of Automation,Xi＇an University of Posts ＆ Telecommunications,Xi＇an 710121)
出处
《计算机与数字工程》
2018年第8期1643-1646,1658,共5页
Computer & Digital Engineering
关键词
直线检测
数学形态学
车牌定位
检测模板
straight line detection
mathematieal morphology
license plate loeation
detection template
