摘要
提出了一种基于HSV空间和纹理特征的快速车牌定位方法.该算法利用车牌区域固定的颜色特征,可快速、准确地定位到与车牌颜色有关的区域.针对不同的背景和不同的车辆,抽取了150幅图片进行测试,定位成功率为97.6%,平均定时耗时为28 ms.实验表明,该方法是一种在HSV空间利用颜色和纹理特征进行定位的算法,通用性强,灵活有效.
The paper presents a fast vehicle plate location method based on HSV space and texture, which makes full use of the characteristic that license plates have relatively steadfast color to quickly and accurately locate areas related to the color. It is a precise plate locating algorithm based on color features in HSV space and texture,which is effective and has high universality. In the experiment, 150 images taken from various vehicles and different scenes are employed, the license plate location rate of success is 97.6%, and the average time that each location needs is 28 ms.
出处
《重庆工学院学报(自然科学版)》
2008年第10期179-182,共4页
Journal of Chongqing Institute of Technology