摘要
为了提高车牌自动识别的正确率,提出一种基于蚁群算法优化特征子集和识别器参数的车牌自动识别模型。首先提取车牌轮廓、笔画和灰度特征,然后利用蚁群算法选择最优特征子集,最后采用支持向量机建立车牌自动分类器。仿真结果表明,该模型能够有效特征集中的消冗余和无用特征,快速找到最优车牌特征子集,提高了车牌自动识别正确率和效率,是一种可靠、有效的车牌自动识别方法。
In order to improve the recognition accuracy of license plate recognition, the paper proposed a license plate recognition method based on ant colony optimization algorithm and Support vector machine. Firstly, the plate contour, stroke order and grey features are extracted, and then ant colony optimization algorithm is used to select the optimal features, finally the support vector machine are used to establish license plate classifier and recognized the license plate. The simulation results show that the proposed method can reduce redundant features to get the optimal feature quickly, and improve the license plate recognition accuracy, it is a reliable and valid license plate automatic recognition method.
出处
《科技通报》
北大核心
2013年第9期113-116,共4页
Bulletin of Science and Technology
基金
成都工业学院校级科研项目(项目编号:KY1011010B)
关键词
车牌识别
结构特征
灰度特征
支持向量机
蚁群优化算法
license plate recognition
structural features
grayscale pixel feature
support vector machine
ant colony optimization algorithm