东北大学学报（自然科学版）

东北大学学报(自然科学版) ›› 2011, Vol. 32 ›› Issue (2): 193-196+201.DOI: -

• 论著 • 上一篇    下一篇

基于PSO的Live Wire交互式图像分割算法

依玉峰;高立群;崔兆华;史圣伦;   

  1. 东北大学信息科学与工程学院;东北财经大学会计学院;
  • 收稿日期:2013-06-19 修回日期:2013-06-19 发布日期:2013-04-04
  • 通讯作者: -
  • 作者简介:-
  • 基金资助:
    国家自然科学基金资助项目(60674021)

PSO-based live wire interactive image segmentation algorithm

Yi, Yu-Feng (1); Gao, Li-Qun (1); Cui, Zhao-Hua (1); Shi, Sheng-Lun (2)   

  1. (1) School of Information Science and Engineering, Northeastern University, Shenyang 110819, China; (2) Accountancy College, Dongbei University of Finance and Economics, Dalian 116023, China
  • Received:2013-06-19 Revised:2013-06-19 Published:2013-04-04
  • Contact: Yi, Y.-F.
  • About author:-
  • Supported by:
    -

RichHTML

0

PDF (PC)

951

摘要： 传统Live Wire算法易受伪轮廓干扰,并且算法执行速度较慢.针对这些问题,提出一种基于PSO的Live Wire交互式图像分割算法.算法首先构造新的代价函数,引入相邻节点间梯度幅值变化函数来减轻伪轮廓的干扰,提高了算法的分割精度;其次,为了提高算法的执行效率,应用粒子群算法求取图像中任意两点间最短路径来定位目标边界,并与经典的基于Dijkstra动态规划图搜索的Live Wire算法进行比较.实验结果表明,与传统方法相比,所提算法在分割精度和执行效率上都有很大提高.

关键词: Live Wire算法, 图像分割, 粒子群优化, 最短路径, Dijkstra算法

Abstract: A PSO-based live wire interactive image segmentation algorithm was proposed to solve the problems that the objective contour is easily influenced by imaging artifacts and imaged at low computation speed. With a new cost function formulated, the gradient amplitude change function between adjacent nodes was introduced into the new cost function to reduce the interference due to imaging artifacts and improve the segmentation accuracy. To improve the implementing efficiency of the algorithm proposed, PSO was applied to finding out the shortest path between any two points in image so as to locate the objective edge, and the relevant results were compared with the typical Live Wire image segmentation algorithm based on the search by the Dijkstra algorithm. It was found that the proposed algorithm is more accurate and efficient.

中图分类号: