摘要
针对复杂背景图像下的车牌定位问题 ,文章提出了一种新的方法 ,充分利用字符和车牌背景的灰度特征及其二维分布规律 ,采用关键点取样、分格操作和两次定位操作 ,很好地兼顾了定位的正确性和快速性。定位正确率为 98.3 % ,平均定位时间为 6.8ms。
This paper put forward a new method for vehicle plate location in complicated background, which well compromised both the accuracy and speediness by making use of the gray-level characteristics of characters and background on vehicle plate and its 2-D distribution regulation, sampling the key pixel, plotting grid and locating operation twice. The location correctness is 98.3%. And the average location time is 6.8 ms.
出处
《交通与计算机》
2004年第5期25-27,共3页
Computer and Communications
