摘要
根据车牌区域的灰度分布特征,提出一种定位车牌区域的新方法.该方法先利用车牌区域灰度分布特征,对车辆图片进行粗定位并得到车牌上下边界;再根据车牌区域字符紧密性特征,利用垂直投影方法初步得到车牌的左右边界,最后根据字符宽度和间距进一步修正车牌的左右边界.经实验证明,该方法具有在复杂背景下适应性好、抗干扰、实时性好、定位精确等特点.
According to the gray distribution of license plate,we propose a new method to locate license plate.In this method,we first locate vehicle license plate rough and get the upper and lower boundaries by using the gray distribution features of it.Then,we use the vertical projection to get the left and right boundaries of the license plate initially according to the characteristics of license plate texture and character closely.Finally,we amend left and right boundaries of the plate according to the character width and spacing.The experiment proved that the method has good adaptability in a complex background,anti-interference,real time,accurate location and so on.
出处
《微电子学与计算机》
CSCD
北大核心
2011年第10期1-3,8,共4页
Microelectronics & Computer
基金
国家自然科学基金项目(50674086)
关键词
车牌定位
灰度分布特征
字符紧密性
垂直投影
license plate location
distribution of gray
characteristic of character closely
vertical projection
