中文摘要：

利用粒子群算法全局性和鲁棒性的特点,可以解决模糊C均值算法（FCM）用于图像分割时对初始值敏感、容易陷入局部极小值的问题。但是设定粒子群算法的初始搜索范围依赖于人的经验,并且所设范围往往过大,影响算法的执行速度,为此提出用收敛速度快的K均值聚类法得到的聚类中心作为粒子群算法初始搜索范围的参考,缩小粒子群算法的搜索范围,提高算法执行速度。实验表明该算法具有较高的分割速度和良好的抑制噪声的能力。

英文摘要：

The fuzzy C-means algorithm is sensitive to noise and always converges to the local infinitesimal value, which is overcome by PSO algorithm with the feature of overall robustness. But the initial searching scope of PSO was selected by hu- man experience, and the selected searching scope was always too big, which influenced the velocity of algorithm. This paper used the clustering centers obtained by K-means algorithm as the reference of the searching scope of PSO algorithm, which reduced the search scope and improved the velocity of algorithm. The experimental results show that new algorithm can converge more quickly than the standard FCM algorithm and suppress the noise effectively.