| 改进的FCM在人脑MR图像分割中的应用 |
| |
| 引用本文： | 吴林,郭大勇,施克仁,郑鹏.改进的FCM在人脑MR图像分割中的应用[J].清华大学学报(自然科学版),2004,44(2):157-159. |
| |
| 作者姓名： | 吴林 郭大勇 施克仁 郑鹏 |
| |
| 作者单位： | 清华大学,机械工程系,北京,100084 |
| |
| 基金项目： | 国家教育振兴计划项目(091202202) |
| |
| 摘 要： | 为解决模糊C-均值聚类(FCM)算法在图像分割尤其是医学图像分割中存在的计算量大、运行时间过长的问题,提出了一种改进方法。利用收敛速度快的K均值聚类法得到的聚类中心作为FCM算法的初始聚类中心,减少FCM算法收敛所需的迭代次数;优化参与迭代运算的数据集,减少每次迭代过程的运算时间。该方法使FCM算法的运算速度提高了将近10倍,而且不会影响算法的分割效果。
|
| 关 键 词： | 图像识别 模糊C-均值 磁共振成像(MRI) 图像分割 |
| 文章编号： | 1000-0054(2004)02-0157-03 |
| 修稿时间： | 2003年5月8日 |
Modified fuzzy c-means algorithm for image segmentation in brain magnetic resonance images |
| |
| WU Lin,GUO Dayong,SHI Keren,ZHENG Peng.Modified fuzzy c-means algorithm for image segmentation in brain magnetic resonance images[J].Journal of Tsinghua University(Science and Technology),2004,44(2):157-159. |
| |
| Authors: | WU Lin GUO Dayong SHI Keren ZHENG Peng |
| |
| Abstract: | The fuzzy C-means clustering (FCM) algorithm requires a long time to segment images, especially medical images, due to processing the large data set. This paper presents a method to speed up the FCM algorithm using cluster centers obtained by the K-means clustering algorithm as the initial cluster centers for the FCM algorithm to reduce the number of iterations required for convergence and for optimization of the data set to reduce the time for each iteration. Test with brain MRI images show that this method accelerates the FCM algorithm by approximately 10 fold while maintaining the segmentation accuracy. |
| |
| Keywords: | image recognize fuzzy C-means magnetic resonance imaging (MRI) image segmentation |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
