Computer Engineering and Applications ›› 2009, Vol. 45 ›› Issue (33): 138-140.DOI: 10.3778/j.issn.1002-8331.2009.33.045

• 图形、图像、模式识别 • Previous Articles     Next Articles

Fast fuzzy C-means clustering algorithm for color image segmentation

DU Hai-shun1,2,WANG Feng-quan2   

  1. 1.Institute of Advanced Control and Intelligent Information Processing,Henan University,Kaifeng,Henan 475004,China
    2.College of Instrument Science & Engineering,Southeast University,Nanjing 210096,China
  • Received:2008-12-04 Revised:2009-01-15 Online:2009-11-21 Published:2009-11-21
  • Contact: DU Hai-shun



  1. 1.河南大学 先进控制与智能信息处理研究所,河南 开封 475004
    2.东南大学 仪器科学与工程学院,南京 210096
  • 通讯作者: 杜海顺

Abstract: A fast fuzzy C-means clustering algorithm for color image segmentation is proposed to solve the problem of heavy calculating burden and the disadvantage that it needs the number of clusters for FCM.It uses watershed transform that is based on gradient image to partition the color image data into a certain number of subsets with similar color firstly,and then centers and sizes of the subsets are used in FCM.The computation speed of the fuzzy clustering algorithm is improved greatly because the number of color image data points used in fuzzy clustering is reduced notably.Furthermore,it can use the cluster validity index to find the number of clusters quickly.Experiments show that without changing the clustering function,the proposed approach has much faster computation speed than FCM algorithm and can segment the color image quickly and effectively.

Key words: fuzzy clustering, watershed transform, color image segmentation

摘要: FCM用于彩色图像分割存在聚类数目需要事先确定、计算速度慢的问题,为此,提出一种快速的模糊C均值聚类方法(FFCM)。首先,对原始彩色图像进行基于梯度图的分水岭变换,从而把原始彩色图像数据分成一些具有色彩一致性的子集;然后,利用这些子集的大小和中心点进行模糊聚类。由于FFCM聚类样本数量显著减小,因此可以大幅提高模糊C均值聚类算法的计算速度,进而可以采用聚类有效性指标确定聚类数目。实验表明,这种方法不需要事先确定聚类数目,在聚类有效性能不变的前提下,可以使模糊聚类的速度得到明显提高,实现了彩色图像的快速分割。

关键词: 模糊聚类, 分水岭变换, 彩色图像分割

CLC Number: