期刊文献+

迭代梯度矢量流变形模型的图象分割方法

Iterative Gradient Vector Flow Snake for Segmentation of Image
下载PDF
导出
摘要 虽然梯度矢量流变形模型是一个有效的2D/3D图像分割的工具,但当图像边缘的凹口又深又细时,变形模型不能进入深凹口,为此提出了迭代梯度矢量流方法。此方法是修正当前梯度矢量流变形模型的收敛结果作为其后梯度矢量流变形模型的初始轮廓,通过梯度矢量流变形模型算法的迭代来完成图像的分割。实验结果证明:迭代梯度矢量流变形模型是解决含有深细凹口边缘图像分割的一种有效方法。 Gradient Vector Flow Snake is one of the most effective tools for 2D/3D image segmentation. But GVF Snake can't move into boundary concavities when the concavities are long and thin. The Iterative GVF Snake is proposed to resolve this problem. The method is iterating GVF Snake by adjusting the result of convergence of current GVF Snake as the initial contour of next GVF Snake. Experiments show that the Iterative GVF Snake performs well for segmentation of images that have thin and long concavities.
出处 《青岛大学学报(工程技术版)》 CAS 2005年第2期84-86,90,共4页 Journal of Qingdao University(Engineering & Technology Edition)
关键词 梯度矢量流 迭代 图像分割 变形模型 ROI 凹口 gradient vector flow iteration segmentation of image snake (or active contour) ROI boundary concavity
  • 引文网络
  • 相关文献

参考文献5

  • 1Kass M, Witkin A, Terzopoulos D. Snakes: Active Contour Models [J]. International Journal of Computer Vision,1988 (1) : 321 - 331.
  • 2Ranganath S. Contour Extraction from Cardiac MRI Studies Using Snake [J]. IEEE Trans on Medical Imaging, 1995,14: 328- 338.
  • 3Leymaire F. Tracking and Describing Deformable Objects Using Active Contour Models [D]. Montreal: McGill University, 1990.
  • 4Xu C, Pham D L, Prince J L. Medical Image Segmentation Using Deformable Models [A]. Sonka M, Fitzpatrick J M.Handbook of Medical Imaging: Vol. 2: Medical Image Processing and Analysis [C]. Washington: SPIE Press, 2000.
  • 5Xu C, Prince J L. Gradient Vector Flow Deformable Models [A]. Bankman Isaac. Handbook of Medical Imaging [C].San Diego: Academic Press, 2000.

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部