摘要
针对汽车牌照的自动识别中倾斜问题,对Hough变换提出了新的用法。首先,根据灰度确定汽车图像中车牌的位置和范围,取出包含车牌的子图像;然后对子图像中的点作二级Hough变换算法,计算出子图像中主要直线的角度,该角度被认为是车牌的倾斜角度;最后,用插值旋转的方法进行校正。仿真实验验证了本文算法的有效性。
A new usage of Hough Transform is introduced in this paper.Firstly,the position and scope of the license plate is located and the image that contains the license plate is picked up.Then, a two-stage Hough transform algorithm is applied to the image to calculate the angle of the main line.This angle is thought as the declining angle of the license plate.Lastly,the orientated image rectified using interpolation rotation method.This algorithm is validated through simulation tests.
出处
《信息与电子工程》
2004年第1期45-48,共4页
information and electronic engineering
