摘要
提出一种基于二值图像灰度变化特征进行车牌精确定位的方法.在车牌粗定位的基础上,对分割出的车牌图像进行二值化,对二值车牌图像进行逐行扫描,利用每一行像素的黑、白跳变规律确定车牌的上下边界;对二值车牌图像进行处理得到特征图像,通过对特征图像进行垂直投影确定车牌左右边界.测试结果表明,该方法精确定位的准确率达到99%.
A method for vehicle license plate accurate localization based on binarized image is presented in this paper. Binarizing the segmented license plate image, the binarized image is scanned line by line on the basis of rough localization, the upper and lower borders are determined through the black-white variation of the pixels in every row. After processing the binarized license plate a characteristic image is obtained. The left and right borders are determined based on the vertical projection of the characteristic image. Testing results show that the presented method has an accurate localization rate of 99%.
出处
《东南大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2005年第6期972-974,共3页
Journal of Southeast University：Natural Science Edition
基金
江苏省自然科学基金资助项目(BK2004077)
东南大学预研基金资助项目(XJ0521205)
关键词
车牌定位
二值化
纹理
图像识别痧
license plate localization
binarization
texture
image recognition
