计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (9): 181-184.

• 图形、图像、模式识别 • 上一篇    下一篇

混合聚类彩色图像分割方法研究

施海滨，周 勇   

  1. 中国矿业大学 计算机科学与技术学院，江苏 徐州 221116
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-03-21 发布日期:2011-03-21

Research for color image segmentation based on hybrid clustering

SHI Haibin，ZHOU Yong   

  1. School of Computer Science and Technology，China University of Mining and Technology，Xuzhou，Jiangsu 221116，China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-03-21 Published:2011-03-21

PDF

摘要： 提出了一种基于K-均值算法和EM算法混合聚类的彩色图像分割方法。首先将待分割的RGB彩色图像转化成YUV空间模型，然后将该图像分割成n小块，对每个块的颜色分量用改进的K-均值聚类算法进行聚类分析，最后用EM聚类算法对每个块进行聚类，分割源图像。对K-均值算法和EM算法的初始聚类中心引进了改进算法，加快了算法的收敛速度。并与相似的分割方法进行了比较实验，给出了详细的实验结果与分析。实验表明该方法分割速度快，效果好，具有较高的实用价值。

关键词: 图像分割, 期望最大化（EM）算法, K-均值算法, YUV颜色空间

Abstract: A new color image segmentation algorithm is introduced based on hybrid clustering including K-means algorithm and EM algorithm，which firstly converts RGB color image into YUV-Space model，and then divides the whole image to n-blocks，clusters the color components of each block with K-means improved in this paper，and finally，segments the source image by clustering each block with EM clustering algorithm.In this paper，a new method is proposed to set initial cluster centers in K-means algorithm and EM algorithm，accelerates the convergence speed.The experiment results and the comparison results with similar approach are provided.Experiment results show the proposed algorithm is effective and has high practical value.

Key words: image segmentation, Expectation-Maximization（EM） algorithm, K-means algorithm, YUV color space

京ICP备13024262号-1
Copyright © 《计算机工程与应用》编辑部
技术支持：北京玛格泰克科技发展有限公司
总访问量
今日访问
在线人数