车辆牌照定位的算法研究

Algorithm Study for Location of Vehicle License Plate

车辆牌照的自动识别是智能交通系统（ＩＴＳ）中的关键技术．而车牌照的定位又是车牌识别的关键点之一．本论文探索用数学形态学和投影方法来确定车牌照在原始灰度图象中的水平和垂直位置，从而定位车牌照图象．对不同背景和光照条件下的各类车辆灰度图象进行实验的结果表明本论文提出的车辆牌照定位算法是一种可行的车牌定位方法．

Automatic recognition for vehicle license plates is one of the critical techniques for the intelligent transportation system (ITS), in which location of vehicle license plate play the most important role. This paper proposes an effective method for the application of vehicle license plates recognition. Projective histogram and gray-scale morphology are used in determining the horizontal and vertical location of license plates. The plate area is thus segmented from the input gray-scale image. Result of evaluation tests based on a series of pictures of various backgrounds taken at different ill umination demonstrated that the al gorithms in the paper are relatively robust.