基于级联卷积网络的自然场景下的车牌检测  

Detecting license plate in natural scenes based on cascade convolutional networks

作　　者：闫鹏[1] 牛常勇[1] 范明[1] 

机构地区：[1]郑州大学信息工程学院,河南郑州450052

出　　处：《计算机工程与设计》2014年第12期4296-4301,共6页Computer Engineering and Design

摘　　要：为有效解决自然场景下车牌检测的分类效率和分类准确率之间的矛盾,提出一种鲁棒的快速车牌检测方法。以整个车牌作为训练和检测的基本单位,直接使用卷积网络作为检测器,级联多个卷积网络,对自然场景下的车牌进行检测。通过引入卷积网络作为基本的学习子单元,进一步把多个子单元组织成级联结构,满足了自然场景下的车牌检测对检测准确率和检测效率的要求。在现实数据上的实验结果表明,级联卷积网络在保证较低误报率的同时具有较高的检测率和检测效率。To solve the problems of detecting license plate in natural scenes with scene complexity,data intensity,various illumination and view angle,a robust and fast architecture for license plate detection in natural scenes was propose.By introducing the convolutional network as the basic learning unit and further cascading the basic ones into more complex architecture,this method tried to achieve competitive detection rate with improved efficiency for the natural scene plate detection problem.Empirical results show that the propose method can yield high detection rate with efficiency on a real-world dataset under reasonable false positive rate.

关 键 词：车牌检测 卷积网络 级联分类器 自然场景 误报率 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]