基于纹理特征的自适应车牌定位方法

车牌定位是智能交通管理中一个重要的环节,通过提出一个运算简单、运行速度快的车牌定位方法,使用自适应灰度差阈值生成二值图,它是纹理清晰、边缘表现突出,且夜晚图像也能生成效果较好的二值图.在车牌定位的步骤中,通过对二值化后车辆图像特征的分析,采取了图片自下而上扫描,对扫描行连续跳变点数目进行计数,并设置跳变点间最大间距、车牌有效行数和区域长宽比,准确地找出图片中车牌的位置.

A Self-adaptive License Plate Location Way Based on Textural Features

License plate location is the most important link in the intelligent traffic system. The thesis puts forward a simple and high speed way of license plate location. The method makes use of the self- adaptive threshold of gray scales difference to creat binary image, and can create clearer and high- quality binary images. In the step of license plate location, it can analyze the characteristics of the bi- nary images and scan these images from bottom to top, measure the number of continuous leap points, and set the maximum scanning distance, continuous leap lines and length-width ratio, it can find the location of the license plates correctly.