计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (31): 196-198.DOI: 10.3778/j.issn.1002-8331.2010.31.054

• 图形、图像、模式识别 • 上一篇    下一篇

经验模态分解和形态学在图像边缘检测中的应用

蔡剑华1,2,胡惟文1,王先春1   

  1. 1.湖南文理学院 信息研究所,湖南 常德 415000
    2.中南大学 信息物理工程学院,长沙 410083
  • 收稿日期:2009-03-17 修回日期:2009-05-15 出版日期:2010-11-01 发布日期:2010-11-01
  • 通讯作者: 蔡剑华

Edge detection of image using empirical mode decomposition and morphology

CAI Jian-hua1,2,HU Wei-wen1,WANG Xian-chun1   

  1. 1.Information Institute,Hunan University of Arts and Science,Changde,Hunan 415000,China
    2.School of Info-physics and Geomatics Enginerring,Central South University,Changsha 410083,China
  • Received:2009-03-17 Revised:2009-05-15 Online:2010-11-01 Published:2010-11-01
  • Contact: CAI Jian-hua

摘要: 针对传统边缘检测算法存在的边缘分辨率较低、抗干扰性较差等问题,提出了一种基于二维经验模态分解和数学形态学结合的图像边缘检测算法。从二维经验模态分解理论出发,把图像分解为多尺度下的细节和轮廓,对图像分解的弱边缘信息适当加强;从灰度形态学的角度出发,对加强边缘信息的图像,进行腐蚀或膨胀以及边缘提取,得到其边缘。实验结果表明,该方法在有效抑制噪声的同时,实现了边缘的精确定位,细节提取效果良好。

关键词: 图像处理, 边缘检测, 二维经验模态分解, 数学形态学

Abstract: Considering the shortcoming of traditional methods,a new approach combinig Bidimensional Empirical Mode Decomposition(BEMD) with morphology of edge detection is proposed.Firstly by the BEMD,this paper decomposes the original image to detail part and contour part,which are handled independently.Using the multi-scale decomposition strengthens the weak parts of the image edge appropriately.Then,it gives edge detection from the perspective of gray morphological and gets the edge information.The results show that the theory proposed has great effects in edge accuracy,strong and weak edge extraction and noise suppression.

Key words: image processing, edge detection, bidimensional empirical mode decomposition, mathematic morphology

中图分类号: