首页 | 本学科首页   官方微博 | 高级检索  
     

利用Hough变换和先验知识的车牌字符分割算法
引用本文:张云刚,张长水.利用Hough变换和先验知识的车牌字符分割算法[J].计算机学报,2004,27(1):130-135.
作者姓名:张云刚  张长水
作者单位:清华大学自动化系信息处理研究所,北京,100084
摘    要:随着科技的发展,车牌识别系统得到了很多应用。车牌识别系统包含三个部分:车牌定位、字符分割和字符识别。车牌字符分割是车牌自动识别系统中的重要步骤。车牌字符分割中存在噪声干扰、边框影响、铆钉和间隔符影响、车牌旋转、光照不均等问题。这些问题容易造成分割不准确,甚至分割错误。针对这些问题,该文提出了一种先分段,再利用Hough变换拟合直线的水平分割方法和基于先验知识约束的垂直分割方法,同时提出目标增强的预处理方法。大量实验表明,该算法较好地解决了以上问题,适用于各种质量的车牌图像,分割的准确率较高。

关 键 词:车牌字符分割算法  Hough变换  先验知识  字符识别  预处理算法

Segmenting Characters of License Plate by Hough Transformation and the Prior Knowledge
ZHANG Yun,Gang,ZHANG Chang,Shui.Segmenting Characters of License Plate by Hough Transformation and the Prior Knowledge[J].Chinese Journal of Computers,2004,27(1):130-135.
Authors:ZHANG Yun  Gang  ZHANG Chang  Shui
Abstract:There are many useful applications for a LPR (License Plate Recognition) system. The LPR algorithm consists of three steps: license plate locating, character segmentation and character recognition. Character segmentation is an important step in a LPR system. There are many factors that cause the character segmentation task difficult, such as image noise, plate frame, rivet, space mark, plate rotation and illumination variance. This paper presents a new algorithm for character segmentation, using Hough transformation and the prior knowledge in horizontal and vertical segmentation respectively. Furthermore, an object enhancement technique is used in image preprocessing. The algorithm overcomes the difficulties mentioned above and avoids the abruption and conglutination of characters that are the drawbacks of image binarization algorithms. And the segmentation is more accurate and robust than simple projection methods. The experiment results show the good performance of the segmentation algorithm.
Keywords:license plate recognition  character segmentation  object enhancement  Hough transformation  prior knowledge
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号