基于边缘检测及灰度跳变的车牌定位算法研究

摘要

In order to accurately locate the vehicle license plate in the complicated background and different illumination conditions, this paper proposes a vehicle license plate location algorithm based on edge detection and gray level jump. Firstly, the obtaining images are preprocessed by graying and binary, improving the quality of image and highlighting the information of the vehicle license plate. And then, the plate images are detected edge of image. Based on this, the border of plate of the license plate region are determined by the gray level jump statistics of horizontal direction and the vertical direction, so as to achieve the location of vehicle license plate. The experimental results show that this method can be more accurate and quicker to realize the location of the vehicle license plate region.%为了能在复杂背景及不同光照条件下准确地定位出车牌，提出了一种基于边缘检测和灰度跳变的车牌定位算法。该算法首先对获取的图像进行灰度化、图像二值化等预处理操作，提高图像质量，突出车牌信息，接着对车牌图像进行边缘检测，在此基础上采用水平方向和垂直方向上的灰度跳变统计来确定车牌区域的上下边界和左右边界，从而实现车牌定位。实验结果表明，该方法可以比较准确、快速地实现车牌区域的定位。