作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2007, Vol. 33 ›› Issue (17): 204-207. doi: 10.3969/j.issn.1000-3428.2007.17.070

• 人工智能与识别技术 • 上一篇    下一篇

基于水平梯度和形态学分析的车牌实时定位方法

于深洋,黄剑华,刘家锋 ,唐降龙,赵 薇,刘松波   

  1. (哈尔滨工业大学计算机科学与技术学院,哈尔滨 150001)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-09-05 发布日期:2007-09-05

Approach of License Plate Locating Based on Horizontal Grads
and Morphology Analysis

YU Shen-yang, HUANG Jian-hua, LIU Jia-feng, TANG Xiang-long, ZHAO Wei, LIU Song-bo   

  1. (School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001)
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-09-05 Published:2007-09-05

摘要: 车牌图像定位是车牌照识别系统的关键,该文提出了一种在高速公路复杂背景下的车牌定位与车牌字符分割方法。该方法利用水平相关特征、车牌区域的梯度形态特征和车牌配色特征进行车牌定位,并利用车牌的结构特征采用多尺度模板匹配方法切分车牌字符。实验表明该方法在复杂背景下具有较好的定位切分效果和较强的鲁棒性。

关键词: 车牌检测和定位, 水平梯度, HSV色彩分割, 多尺度模板字符分割

Abstract: Vehicle license plate locating is of vital importance in license plate recognition system. This paper proposes a new license plate detection and character segmentation method. The horizontal correlating feature of characters, grads shape and color feather of license plate are taken into consideration to the location of license plates. Multiple scale template matching is applied for license plate characters segmentation using structural information of license plates. Experiments show that the proposed method is reliable and robust in complex environment in actual application.

Key words: license plate detecting and locating, horizontal grads, HSV color segmentation, multiple scale template character segmentation

中图分类号: