AdaBoost算法在车牌字符识别中的应用

Application of AdaBoost Algorithm on License Plate Recognition

季秀霞

提出了一种基于AdaBoost的车牌字符自动识别算法。AdaBoost是一种构建准确分类器的学习算法，它将一族弱学习算法通过一定规则结合成为一个强学习算法，从而通过样本训练得到一个识别准确率理想的分类器，将之用于车牌字符识别，对车牌图像进行实验，对车牌字符样本进行特征提取，用特征来训练有效分类器，用MATLAB完成了对车牌照数字识别的模拟，结果证实此算法对车牌字符识别有一定准确性，具有良好的效果。[著者文摘]

A method of License Plate Recognition using AdaBoost algorithm is presented.AdaBoost is a learning algorithm for constructing accurate classifiers, It can obtain a strong learning algorithm by combining a series of weak learning algorithms through some rules, which is used on License Plate Recognition, Selecting character features, trains the effective classifier with features, simulates the recognition in use of MATLAB, the result of simulation indicated that the method of this paper proposed has the good effect.[著者文摘]

车牌识别技术在中山市城区收费站的应用

梁立新

城市路桥收费站应用车牌自动识别技术，可以加强次票收费站管理，有效拦截本地未交年费的车辆，同时可以充当治安卡口配合公安部门稽查盗抢车辆、肇事逃逸车辆，还可以对经常过往的车辆实现自动打票功能，以期降低收费人员的工作强度。此外，随着“车牌自动识别”功能的实现，可以进一步细分车辆通行数据，提供更多的统计信息。[著者文摘]

基于特征投影和交叉覆盖神经网络的车牌识别

License Plate Location Based on Projection Character and Alternate Covering Neural Network

宓浩 张燕平

汽车牌照的自动识别在智能交通系统中占有重要地位，应用前景广阔。在自动识别过程中，牌照中的数字和汉字具有数量少和字体特征固定的特点，故其投影特征明显，利用此性质可以对车牌汉字进行快速分类，但精度不高。神经网络分类准确，且有很强的鲁棒性，但运算量大，识别时间太长且数据不易收敛。文中提出的基于投影和交叉覆盖神经网络的车牌识别方法充分融合利用了两者的优点，克服了各自的不足，达到了较好的结果。[著者文摘]

The recognition of vehicle license plate plays a very important role in intelligence transportation system. It has wide application ranges. In automatic recognition process, the Chinese character in the car license has the quantity to be few and the font characteristics are inherent, therefore its projection characteristic is obvious. Using projection characteristic to recognize license plate can be used for rapid classification. But the precision is not high. Neural network classification is accurate, and has strong robusmess, but the operation is large, also not easy to restrain. In this paper, license plate location based on projection character and alternate covering neural network method can be used to combine the advantages of them, and overcome the shortcomings of them, so it can achieve better results.[著者文摘]

电子车牌识别系统的开发及应用前景分析

Development of Identifying System of Electronic License Plate and Its Applied Vistas

陈吉阳

对电子车牌识别系统的技术开发和应用前景作了阐述，并对其在各相关领域中的应用进行了介绍和分析。[著者文摘]

The paper expounds the development of identifying system of electronic license plate and its applied vistas, introduces and analyses application of it in correlative domains.[著者文摘]

基于粗网格神经网络的车牌字符识别方法

The Recognition of Vehicles＇ License Plates Characters Based on Rough Grid Neural Network

吴成东[1] 刘文涵[1] 傅小菲[2] 丛明[1]

目的为了进一步提高交通车牌字符自动识别能力．方法通过对车牌识别技术国内外现状的分析和对各类车牌识别技术的对比说明，提出了一种基于粗网格神经网络的车牌文字识别方法．该方法先将车牌字符进行预处理，用改进的粗网格法提取字符特征，并用神经网络识别车牌字符．结果在实验过程中所用的字符是从实际拍摄的车辆牌照图像中提取的汉字、英文大写字母和数字．人工提取的汉字种类覆盖了我国现有车辆牌照中出现的大部分汉字，而字母和数字的覆盖率为100％．从实验结果看：数字、字母的识别率比较高，尤其是数字，其识别率达到了99．16％．结论实验表明：数字、字母易于准确地提取特征，粗网格神经网络车牌字符识别方法具有较高的识别精度和实用价值．[著者文摘]

the paper aims to recognizing vehicles＇ license plates characters via analysis of intelligent algorithms deployed on recognition of vehicles＇ license plates. The method of recognizing rough grid features based on neural network are proposed, after literature review and comparison of generally used recognition method on vehicles＇ license plates. In this method, character images are preprocessed at the beginning, then the improved rough grid features are extracted from the original images, and finally the extracted features were used to train the neural network. All the characters used in the case study, such as Chinese characters, capital English letter, number are extracted from real image. The artificially extracted Chinese characters can cover the mostly used Chinese characters on vehicles＇ license plates and the extracted English letter and number totally match the real situation. The recognition rate on number and letter are very high. The recognition rate on number is 99.16 %. The results show that the proposed rough grid features recognition method is feasible and effective.[著者文摘]

智能车牌识别技术

赵素蕊[1] 柳冬青[2]

本文主要介绍了智能车牌识别系统中车牌定位与识别模块的有关技术。[著者文摘]

车牌识别和电子警察的典型应用

随着城市交通智能化的深入，智能交通系统正向系统化方向发展。目前的ITS系统不再是简单的车辆处理系统，而是涵盖道路监控、车辆记录、违章处理、高／快速路管理、智能停车管理等多个方面的综合化系统。各个ITS厂商通过自己的不断努力为各地“平安大道”建设提供了全面系统的技术支持。随着ITS技术的不断改进完善，城市ITS用户以提供高可靠性、高稳定性、高实用性、高灵活性产品的厂商为第一选择，辅助以完善全面的系统集成方案实现城市交通的真正智能化。面对中国道路交通发展的突飞猛进，ITS厂商始终以提供优越品质的ITS系统为目标，提供完善的全程服务为己任，为提升ITS市场的科技水平而不断努力。下面将为大家介绍以下各个系统的一些行业特点。[第一段]

基于机器视觉实现电子警察系统车牌识别功能“计量”确认方法

The Identifying Method of Recognition Rate of Vehicle Registration Platebased on Machine -vision for Electronic Police System

方强

为解决电子警察系统号牌识别率的计量问题，本文研究了机动车退化（模糊）图像的生成过程，将实验室（或野外）严格控制条件下的图像为过渡图片，建立了因机动车运动造成图像退化（模糊）的计算模型，获得退化图片用于号牌识别率的确定。模型能保证成像的曝光时间、响应特性、光照特征等复杂因素的可控性，实验程序证明了本方法的可行性。[著者文摘]

基于方向轮廓的小波分解车牌字符识别方法

A Method of Vehicle Plate Character Recognition Under Multi-scale Directional Contours with Wavelet Transform

秦钟 徐建闽 史胜利 黄海英

字符识别是车牌识别的技术核心。本文提出了一种快速的车牌字符识别方法。首先提取字符的外轮廓。根据小渡分解变换的性质，对字符轮廓进行多分辩分解，得到低分辨率下字符轮廓的近似，通过计算待识别字符与参考字符在多尺度下的轮廓之间的相似度，判别待识别字符与参考字符的匹配程度，最终确定匹配字符。本文对字符匹配算法进行了改进．加快了匹配速度，提高了匹配的可信度。利用本文算法，对1200幅车牌字符图像的识别，准确率达到95．4％，单字符识别平均耗时约为10ms。[著者文摘]

Character recognition is key of license plate recognition . A novel method to recognize the character is proposed in this paper. First, getting the directional contour of the character, the approximately contour was picked by decomposing with wavelet transform. Detecting the similitude of multi-scale contours between the character waiting for recognizing and the referenced character by calculating their comparability ,finally, the matched character was got. The match algorithm was modified in the paper which speedup the match and enhance the reliability. Experiments had been conducted, 1200 vehicle character images were tested, the accuracy was 95.4% and the average consuming time was 10ms.[著者文摘]

车牌识别算法的研究与实现

Research and Realization of License Plate Recognition Arithmetic

何铁军 张宁 黄卫

介绍一种基于KL变换的车牌识别算法。算法主要由车牌分割和车牌字符识别组成。车牌分割算法利用车牌的纹理特征和形状特征来定位车牌，并采用投影的方法和先验知识实现车牌的倾斜校正和字符切分；车牌字符识别算法采用一种最优变换，KL变换来提取字符图像的特征值和特征向量，并通过计算待识别字符与各样本字符特征值的欧氏距离来实现对该字符的分类。试验结果表明此方法是正确的。[著者文摘]

The authors present vehicle license plate recognition algorithm based on KL transform .This algorithm is made up of two parts： plate segmentation and character recognition.In the license plate segmentation algorithm, the character of texture and shape of the plate is utilized to locate the license plate, and image projection and prior knowledge is utilized to detect the skew of the license plate and extract characters from it. In the character recognition algorithm, KL transform, a kind of optimal transform, is applied to extract the eigenvalue and eigenvector from character images. Euler distances of this eigenvalue between recognizing character and sample characters are computed and compared to determine the classification. The validity of this algorithm is proved by test..[著者文摘]