• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Computer Applications in Industry and Engineering >A TRAINABLE LICENSE PLATE RECOGNITION SYSTEM
【24h】

A TRAINABLE LICENSE PLATE RECOGNITION SYSTEM

机译：可培训的牌照识别系统

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Making a system, which automatically recognizes the license plate of car requires an integration of many computer vision problem solvers. These problem solvers are often difficult to implement with algorithmic methods as the problems themselves are not well defined. This paper presents a learning-based approach for the construction of license plate recognition system. It is consisted of three modules. They are respectively, car detection module, license plate segmentation module and recognition module. Car detection module detects a car in the given image sequence obtained from the camera with simple color-based approach. Segmentation module extracts the license plate from the detected car image using support vector machines (SVMs) as filters for analyzing the color and texture properties of license plate. Recognition module then reads characters in the license plate with neural network (NN)-based character recognizer. The system has been tested with 1000 video sequences obtained from tollgate and parking lot, etc. and has shown the following performances on average: Car detection rate 100%, segmentation rate 97.5%, and character recognition rate about 97.2%.
机译：制作一个能够自动识别汽车牌照的系统，需要集成许多计算机视觉问题解决者。这些问题解决者通常很难用算法方法来实现，因为问题本身没有得到很好的定义。本文提出了一种基于学习的车牌识别系统构建方法。它由三个模块组成。它们分别是汽车检测模块，车牌分割模块和识别模块。汽车检测模块使用简单的基于颜色的方法检测从相机获得的给定图像序列中的汽车。分割模块使用支持向量机（SVM）作为过滤器从检测到的汽车图像中提取车牌，以分析车牌的颜色和纹理特性。然后，识别模块使用基于神经网络（NN）的字符识别器读取车牌中的字符。该系统已经对从收费站和停车场等处获得的1000个视频序列进行了测试，平均表现出以下性能：汽车检测率100％，分割率97.5％和字符识别率约97.2％。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号