欢迎访问《图学学报》 分享到：
图学学报

图学学报

• 应用与交流 • 上一篇    下一篇

一种改进的Roberts 和灰色关联分析的边缘检测算法

  

  • 出版日期:2014-08-30 发布日期:2015-05-05

An Improved Image Edge Detection Algorithm Based on Roberts and Grey Relational Analysis

  • Online:2014-08-30 Published:2015-05-05

PDF (PC)

234

被引次数

46

摘要： 针对Roberts 算子容易漏检及对噪声较敏感的问题，提出一种改进的基于灰色关
联分析方法的边缘检测算法GRA-Roberts。通过改进Roberts 算子提高其检测精度和抗噪性能，
结合灰色关联分析方法，将改进后的Roberts 算子作为参考序列，通过计算灰色关联度来检测
图像边缘。实验结果表明，GRA-Roberts 算法能有效克服Roberts 算子算法易漏检和对噪声敏
感的问题，且比其他灰色关联结合算法具有更好的检测效果。

关键词: Roberts 算子, 灰色关联分析, 抗噪性, 边缘检测

Abstract: Aiming at the problems of Roberts operator being easy to miss detection pixels and sensitive
to noise, an improved edge detection algorithm GRA-Roberts is proposed. By improving the Roberts
operator, the precision and the anti-noise performance is enhanced. Combined with the grey relational
analysis, referring to the improved Roberts operator, the image edge is detected based on the grey
relational grade. The experiment results show that GRA-Roberts can not only get over the above
drawbacks of the Roberts operator algorithm effectively, but also get better detection effects compared
to other related grey relational algorithms.

Key words: Roberts operator, grey relational analysis, anti-noise, edge detection