计算机与现代化

• 图形图像处理 • 上一篇    下一篇

基于S变换融合Canny算子的汽车轮廓提取

  

  1. 天津大学管理与经济学部,天津300072
  • 收稿日期:2014-01-02 出版日期:2014-04-17 发布日期:2014-04-23
  • 作者简介:作者简介:吴震菊(1976),女,河北唐山人,天津大学管理与经济学部硕士研究生,研究方向:计算机应用。

Extraction for Vehicles Contour Based on Stransformation Coupled Canny Operator

  1. College of Management and Economics, Tianjin University, Tianjin 300072, China
  • Received:2014-01-02 Online:2014-04-17 Published:2014-04-23

摘要:  

摘要: 为了克服当前的Canny算子对噪音敏感、易出现虚假边缘等不足,并能更好地提取汽车轮廓,显著提高其精度,本文提出S变换融合Canny算子的汽车轮廓提取机制。将S变换引入到Canny算子中,利用S变换的中频系数进行轮廓提取,显著提高了抗噪音干扰能力,并使得Canny算子具备识别虚假轮廓信息能力。在Matlab仿真平台上测试了本文机制及其它几种算子的性能。仿真结果显示:与其他几种提取机制相比,本文机制所提取的汽车轮廓精度最高,抗噪音干扰能力最强,信噪比达到32.675。

关键词: S变换, Canny算子, 抗噪音, 虚假边缘, 轮廓提取

Abstract:  

 Abstract:  In order to overcome these defects such as sensitive to noise and prone to produce false edges for better extracting the car contour to significantly improve the accuracy, the extraction mechanism for vehicles contour based on Stransformation coupled Canny operator is proposed in this paper. The Stransformation is introduced into the Canny operator, and the intermediate frequency coefficient of Stransformation is used to extract contour. It significantly improves the ability of antinoise interference, and makes the Canny operator having the property of identifying the false edge information. This algorithm and other algorithms are tested by the Matlab simulation platform. And the results show that: comparing with the other extraction mechanism, the contour extraction accuracy of this mechanism is the highest, and the ability of anti noise interference is also the strongest for which its peak signal noise ratio up to 32.675.
 Key words:  Stransformation; Canny operator; antinoise; false edges; contour extraction

Key words:

中图分类号: