摘要
提出了一种将模板匹配、形态学和投影法多方法融合的车牌定位算法。首先,对预处理后的车牌图像采用优化的模板匹配算法粗定位车牌区域;然后运用形态梯度方法对粗定位后的图像进行边缘检测;最后,采用投影法进行精确定位,通过对投影的分析找到车牌的准确位置。实验结果表明,该算法对车牌定位的准确性和处理速度都有很大提高,满足了系统实时性和准确性的要求。
In order to realize the location of the target, a license plate location method is proposed, which integrates template matching, morphology and projection method, First, this algorithm which is applied to the license plate image after being preprocessed locates the license plate approximately with optimal template matching. Then edge detect the image of coarse location based on morphological gradient method. Finally,the method of projection is applied to the exact location and the license plate location can be got through projection analysis. The experiment results indicate that the algorithm given is able to improve the veracity and enhance the speed. It can satisfy real time and veracity requirements of the system.
出处
《自动化应用》
2010年第1期62-64,共3页
Automation Application
基金
教育部重点实验室资助项目(No.2006-28-6)
关键词
多方法融合
车牌定位
模板匹配
形态梯度
投影分析
combination of several algorithms
license plate location
template matching
morphological grads
projection analysis
