摘要
文章提出了一种基于聚类分析分割车牌字符的方法。即按照属于同一个字符的象素构成一个连通域的原则,再结合牌照的先验知识,较好解决了汽车牌照在复杂背景条件下的字符切分问题。
This paper presents a Cluster-Based method to segment the characters of license plate.It follows a principle that the pixels which belong to a character form a connective region,then combines with empirical knowledge of license plate,successfully solves the problem of the characters' segmentation under complex background conditions.
出处
《计算机工程与应用》
CSCD
北大核心
2002年第6期221-222,256,共3页
Computer Engineering and Applications
基金
武汉市重点科技攻关计划项目资助(编号:20001010094)
