摘要
等周分割是一种基于图谱理论的分割算法,能有效提高图像分割质量且有较高的效率及稳定性。本文提出了一种融合块结构的等周分割算法。该算法采用块结构来减少图中节点数并根据CT图像特征,将该算法应用到CT图像分割中。实验结果表明,融合块结构的等周分割算法在CT图像分割中取得较好的分割效果,并大大提高了分割效率。
Isoperimetric Graph partitioning is a segmentation algorithm based on spectral graph theory, producing high quality segmentations with improved speed and stability. An algorithm based on block structure and isoperimetric algorithm is introduced, using block structure to reduce the number of the nodes in the graph, And with the thought of the feature of the CT image, this algorithm is used to segment CT image. The results of the experiment show that the algorithm based on block structure and isoperimetric algorithm produces good segmentation of the CT image with improved speed.
出处
《世界科技研究与发展》
CSCD
2011年第6期1030-1032,共3页
World Sci-Tech R&D
基金
国家科技重大专项(2008ZX07315-001)
重庆科技攻关项目(CSTC
2008AB5038)
中央高校基本科研业务费(CDJXS10181131)资助项目
关键词
图像分割
CT图像
块结构
等周分割算法
image segmentation
CT image
block structure
isoperimetric segmentation algorithm
