计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (27): 24-27.DOI: 10.3778/j.issn.1002-8331.2009.27.008

• 博士论坛 • 上一篇    下一篇

一种改进的双模态图像分割算法

吴继明1,2,熊建文2,朱学峰1   

  1. 1.华南理工大学 自动化科学与工程学院,广州 510640
    2.华南师范大学 物理与电信工程学院,广州 510631
  • 收稿日期:2009-06-24 修回日期:2009-07-27 出版日期:2009-09-21 发布日期:2009-09-21
  • 通讯作者: 吴继明

Improved segmentation algorithm for bimodal image

WU Ji-ming1,2,XIONG Jian-wen2,ZHU Xue-feng1   

  1. 1.School of Automation Science and Engineering,South China University of Technology,Guangzhou 510640,China
    2.School of Physics and Communication Engineering,South China Normal University,Guangzhou 510631,China
  • Received:2009-06-24 Revised:2009-07-27 Online:2009-09-21 Published:2009-09-21
  • Contact: WU Ji-ming

摘要: 在Mumford-Shah模型基础上提出了一个改进的双模态图像分割算法。该算法基于图像局部化信息创建驱动曲线演化的能量,引入的配准项提高了曲线的演化速度,基于曲线演化竞争的数据拟合项,使得曲线能更稳定地收敛到一个全局静态最小值,且算法对水平集函数初始化位置不敏感。实验结果表明,改进的算法具有收敛速度快、分割结果稳定的特点,尤其在医学CT图像方面具有更强的分割能力,更高的稳定性。

关键词: Mufmford-Shah模型, 双模态图像, 图像分割, CT图像

Abstract: This paper presents a improved segmentation algorithm for bimodal image based on the Mumford-Shah model.The energy which drives the evolution of a curve is constructed based on local image information,the alignment term enhances the speed of curve evolution,and the improved data fitting term which is based on the competition between of the shifted Heaviside functions,makes the curve converge to a better global stationary minimum.The experiments show that the improved algorithm has a faster speed of convergence and a more stable segmentation result,especially has a more powerful ability of segmentation and higher stability in segmentation of medical CT images.

Key words: Mumford-Shah model, bimodal image, image segmentation, CT image

中图分类号: