| 自然场景下的车牌检测与识别算法 |
| |
| 引用本文： | 牛博雅,黄琳琳,胡健.自然场景下的车牌检测与识别算法[J].信号处理,2016,32(7):787-794. |
| |
| 作者姓名： | 牛博雅 黄琳琳 胡健 |
| |
| 作者单位： | 北京交通大学电子信息工程学院,北京 100044 |
| |
| 基金项目： | 国家自然基金面上项目资助(61271306) |
| |
| 摘 要： | 车牌自动识别是智能交通系统的关键技术之一，主要包括车牌检测和字符识别两部分。为提高车牌检测速度和精度，本文提出了一种基于学习、由粗到精的车牌检测方法。首先采用颜色点对和垂直边缘相结合的方法，快速检测出车牌感兴趣区域；然后采用一种基于梯度方向直方图特征和支持向量机的机器学习方法实现车牌的精确定位。在车牌识别阶段，首先采用基于连通域分析与字符固有特征相结合的方法进行字符分割，然后根据字符结构提取3种稳定且有效的特征，采用支持向量机对分割的字符进行识别。采用上述方法对412幅不同角度、不同光照条件、不同时间段下拍摄的图像进行检测与识别，实验结果表明本文提出的算法精度高、鲁棒性好、识别速度符合实时性的要求。
|
| 关 键 词： | 颜色边缘 车牌检测 支持向量机 字符识别 连通域分析 |
| 收稿时间： | 2015-11-03 |
Detection and Recognition Algorithm for License Plate in Natural Scene |
| |
| Affiliation: | School of Electronic and Information Engeering, Beijing Jiaotong University, Beijing 100044, China |
| |
| Abstract: | License plate automatic recognition is one of the key technologies of intelligent transportation system, which contains two parts of license plate detection and character recognition. In this paper, we propose a learning based method using coarse to fine strategy to realize fast and accurate license plate detection and recognition. In detection stage, color pair and vertical edge features are firstly used to find the rough position of the license plate, and then a machine learning method based on HOG feature and SVM classifier is adopted to determine the accurate plate position. In recognition stage, characters are firstly separated based on connected component analysis and the inherent character features, then three kinds of stable and effective features are extracted according to character structures and SVM classifiers are applied to recognize the characters. Experimental results on a database consisting of 412 car images with different viewing angles and different illumination conditions demonstrate the effectiveness of the proposed method. |
| |
| Keywords: | |
|
| 点击此处可从《信号处理》浏览原始摘要信息 |
|
点击此处可从《信号处理》下载全文 |
|
