基于最大流的交互式目标提取算法

被引:2
作者
于丹
汤井田
徐大宏
罗东礼
机构
[1] 中南大学信息物理工程学院生物医学工程研究所
关键词
目标提取; 最大流; 图切割;
D O I
暂无
中图分类号
TP301.6 [算法理论];
学科分类号
摘要
医学图像处理中,目标提取在准确区分组织结构中起了重要的作用,论文介绍了基于最大流的交互式的目标提取算法,该方法把基于区域和基于边界方法结合起来,并用分水岭算法对图像做预分割,在其所分的区域上计算能量函数,然后最小化能量函数求最优边界。笔者结合自己研究的课题,针对目标标记步骤中聚类种子F和#色彩值的k-means算法进行改进,并把改进算法应用到人体器官切片目标分割中。
引用
收藏
页码:246 / 248
页数:3
相关论文
共 8 条
  • [1] probabilistic contour ex-traction withparticles. P′erez P,Blake A,Gangnet M.,JetStream. Proc Int Conf on Computer Vision(IC-CV) . 2001
  • [2] Interactive digital photomontage. AGARWALA A,,DONTCHEVA M,AGRAWALA M,et al. Proceedings of ACM SIGGRAPH . 2004
  • [3] A representation for image structure and its application in object selection with freehand sketches. Tan Kar-Han,Ahuja N. Pro-ceedings IEEE Computer Society Conference on Computer Vision and Pattern Recognition . 2001
  • [4] Interactive segmentation with intelli-gent scissors. Mortensen E N,,Barrett W A. Graphical Models . 1998
  • [5] Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images. BOYKOV Y,JOLLY M-P. Proc IEEE Int Conf on Computer Vision,CD-ROM . 2001
  • [6] Gleicher M,Advanced Technology Group Apple Computer Inc. SIG-GRAPH’95 . 1995
  • [7] Algorithm for solution of a problem of maximum flow in networks with power estimation. Dinic E A. Soviet Mathematics Doklady . 1970
  • [8] Flows in networks[M S.l. Ford L,Fulkerson D. . 1962