东北大学学报（自然科学版）

东北大学学报(自然科学版) ›› 2008, Vol. 29 ›› Issue (5): 645-648.DOI: -

• 论著 • 上一篇    下一篇

辅以CV-GVF方法的测地线活动轮廓模型

崔华;高立群;   

  1. 东北大学信息科学与工程学院;东北大学信息科学与工程学院 辽宁沈阳110004;辽宁沈阳110004
  • 收稿日期:2013-06-22 修回日期:2013-06-22 出版日期:2008-05-15 发布日期:2013-06-22
  • 通讯作者: Cui, H.
  • 作者简介:-
  • 基金资助:
    国家自然科学基金资助项目(60475036);;

Geodesic active contour model aided with CV-GVF method

Cui, Hua (1); Gao, Li-Qun (1)   

  1. (1) School of Information Science and Engineering, Northeastern University, Shenyang 110004, China
  • Received:2013-06-22 Revised:2013-06-22 Online:2008-05-15 Published:2013-06-22
  • Contact: Cui, H.
  • About author:-
  • Supported by:
    -

RichHTML

0

PDF (PC)

534

摘要： 针对经典的测地线活动轮廓对初始位置和噪声比较敏感,在有噪声干扰或初始位置距目标边缘较远时,其往往无法准确收敛到目标边缘的问题,通过将由梯度矢量流和CV方法构成的耦合力场与测地线活动轮廓相结合,提出了辅以CV-GVF方法的测地线活动轮廓模型.实验结果表明,该活动轮廓模型在噪声背景中从无需特别设置的初始位置准确收敛到了目标边缘,对初始位置和背景噪声具有较好的适应性.

关键词: 图像处理, 边缘提取, 活动轮廓模型, 测地线活动轮廓, 梯度矢量流, CV方法

Abstract: Classical geodesic active contour is sensitive to initial location and noise. So, it often fails to converge to the true edge when the initial location is far from target edge or there is noise interference. The geodesic active contour aided with CV-GVF method is therefore proposed by way of combining the geodesic active contour with the coupling force field composed of gradient vector flow and CV method. Experimental results showed that it can converge exactly to the target edge in noise background from any initial location without special setting, i.e., high adaptability to initial location and background noise.

中图分类号: