Computer Engineering and Applications ›› 2008, Vol. 44 ›› Issue (11): 182-183.

• 图形、图像处理 • Previous Articles     Next Articles

Fuzzy particle swarm optimization algorithm for multi-threshold image segmentation

XU Yong-feng,ZHANG Shu-ling   

  1. Department of Mathematic,Northwest University,Xi’an 710069,China
  • Received:2007-07-27 Revised:2007-10-25 Online:2008-04-11 Published:2008-04-11
  • Contact: XU Yong-feng

多阈值图像分割的模糊粒子群优化算法

许永峰,张书玲   

  1. 西北大学 数学系,西安 710069
  • 通讯作者: 许永峰

Abstract: Fuzzy C-mean clustering algorithm is a local search algorithm because it is easily trapped local optimum and is sensitive to initial value effectively.On the other hand,particle swarm optimization algorithm is a global optimization algorithm.By incorporating the local search ability of FCM algorithm and the global optimization ability of PSO and taking the clustering criterion function of FCM as the object function of PSO,a new hybrid multi-threshold image segmentation algorithm based on particle swarm optimization and fuzzy C-mean algorithm is proposed.Experiments show that the new algorithm can get the optimal threshold by the maximum entropy.

Key words: fuzzy C-mean, Particle Swarm Optimization(PSO), image segmentation, multi-threshold

摘要: 把粒子群算法应用到多阈值图像分割中,结合已有的模糊C-均值聚类法提出了一种基于模糊技术的粒子群优化多阈值图像分割算法。FCM聚类算法是一种局部搜索算法,对初始值较为敏感,容易陷入局部极小值而不能得到全局最优解。PSO算法是一种基于群体的具有全局寻优能力的优化方法。将FCM聚类算法和PSO算法结合起来,将FCM聚类算法的聚类准则函数作为PSO算法中的粒子适应度函数。仿真实验表明新算法在最大熵评判准则下能够得到最优阈值。

关键词: 模糊C-均值, 粒子群优化, 图像分割, 多阈值