期刊文献+

水平集方法的改进及在医学图像上的应用

An Improved Level Set Method in Medical Image Applications
在线阅读 下载PDF
导出
摘要 针对水平集方法在运行前需要对图像进行高斯平滑处理,导致提取的结果不准确的缺陷,提出一种水平集的改进算法,通过对水平集的提取结果做聚类区域增长处理,修正水平集对目标的边缘提取。通过对比传统水平集方法和改进后的水平集方法对医学上的细胞图像的处理结果,表明该改进算法能有效提高图像边缘提取的质量。 Level set method needs to process the image applying the Gaussian smoothing way before running,resulting in the inaccurate results after the end of the extracting process.For this reason,this paper puts forward an improved level set algorithm,the algorithm can amend the results of edge extracting through clustering region increasing processing to extracting results of the level set.The experimental results show that the improved algorithm can effectively improve the quality of the image edge extracting by comparing the traditional level set method and the improved level set method for medical image processing results on the cell.
出处 《计算机与现代化》 2010年第12期59-60,64,共3页 Computer and Modernization
关键词 水平集 聚类 边缘提取 医学图像 level set method clustering edge extracting medical image
  • 相关文献

参考文献13

  • 1Luminita A, Vese L, Chan T. A muhiphase level set frame- work for image segmentation using the Mumford and Shah model[ J ]. International Journal of Computer Vision, 2002, 50(3) :271-293.
  • 2Bertalmio M,Sapiro G, Randall G. Region tracking on levelsets methods [ J]. IEEE Trans Medical Imaging, 1999, 18 (5) :448-451.
  • 3Suri J S, Liu Kecheng, Singh S. Shape recovey algorithms using level sets in 2-D/3-D medical imagery. [ J ]. IEEE Trans Information Technology in Biomedical ,2002,6 (4) : 8-28.
  • 4Tsitsiklis J N. Efficient algorithms for globally optimal trajectories [ J ]. IEEE Transactions on Automatic Control, 1995,40 (9) : 1528-1538.
  • 5Sethian J A. A fast marching level set method for monotonically advancing fronts [ C]//Proceedings of the National Academy of Sciences of the United States of America. 1996, 93(4) :1591-1595.
  • 6Chan F T, Vese L. Active contours without edges [ J ]. IEEE Trans on Image Processing,2001 , 10 ( 2 ) : 266-277.
  • 7陈健,田捷,薛健,戴亚康.多速度函数水平集算法及在医学分割中的应用[J].软件学报,2007,18(4):842-849. 被引量:14
  • 8郑罡,王惠南,李远禄.基于Chan-Vese模型的树形结构多相水平集图像分割算法[J].电子学报,2006,34(8):1508-1512. 被引量:20
  • 9董建园,郝重阳,齐敏.基于策略演化水平集的医学图像快速分割[J].中国图象图形学报,2009,14(8):1689-1695. 被引量:5
  • 10Malladi R, Sethian J A, Vemuri B C. Shape modeling with front propagation :A level set approach [ J ]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(2) :158-175.

二级参考文献39

  • 1Osher S, Fedkiw R. Level set methods : An overview and some recent result[J ]. Journal of Computational Physics, 2001,169 ( 2 ) : 463-502.
  • 2Osher S, Sethian J A . Fronts propagation with curvature dependent speed : algorithms based on Hamilton-Jacboi formulation [ J]. Journal of Computational Physics, 1998,79 ( 1 ) :12-49.
  • 3Paragios N, Deriche R. Geodesic active contours and level sets for the detection and tracking of moving objects [ J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(3 ) :266-280.
  • 4Adalsteinsson D, Sethian J A. A fast level set method for propagating interfaces [J]. Journal of Computational Phyxics, 1995,118 (2): 269-277.
  • 5Tsitsiklis J N. Efficient algorithms for globally optimal trajectories [J ]. IEEE Transactions on Automatic Control, 1995, 40 ( 9 ) : 1528-1538.
  • 6Serbian J A. A fast marching level set method for monotonically advanceing fronts [ J]. Proceedings of the National Academy of Sciences, 1996, 93 ( 4 ) : 1591 - 1595.
  • 7Song B, Chan T, A fast algorithm for level set based optimization [R ]. CAM-VCLA, Los Angeles, CA, USA : University of California, 2002.
  • 8Chan T,Vese L. Active contour without edges [J]. IEEE Transactions on Image Processing, 2001,10(2) : 226-277.
  • 9Shi Yong-gang, William C K. A fast level set method without solving PDEs [ A ] . In : Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing[C], Philadelphia, Penn. USA : 2005 : 97-100.
  • 10The Insight Toolkit [ CP/OL], http://www.itk,2006.

共引文献34

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