作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2007, Vol. 33 ›› Issue (13): 191-193,. doi: 10.3969/j.issn.1000-3428.2007.13.065

• 人工智能及识别技术 • 上一篇    下一篇

基于空间势函数加权的模糊C均值聚类分割算法

杨 勇1,黄淑英2, 张 锋3   

  1. (1. 江西财经大学信息管理学院,南昌 330013;2. 江西财经大学电子学院,南昌 330013; 3. 西安交通大学生物医学工程研究所,西安 710049)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-07-05 发布日期:2007-07-05

Fuzzy C-means Cluster Segmentation Algorithm Based on Spatial Potential Function Weighted

YANG Yong1, HUANG Shuying2, ZHANG Feng3   

  1. (1. School of Information Management, Jiangxi University of Finance and Economics, Nanchang 330013; 2. School of Electronics, Jiangxi University of Finance and Economics, Nanchang 330013; 3. Institute of Biomedical Engineering, Xi’an Jiaotong University, Xi’an 710049)
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-07-05 Published:2007-07-05

摘要: 提出了一种基于空间势函数加权的FCM图像分割新算法。该方法将空间邻域的势函数信息融入到原始的FCM算法中,权重在该方法中起核心作用,它是根据最近邻(k-NN)算法的原则将势函数信息扩展到邻域像素中。算法中使用基于统计直方图的快速FCM算法进行初始化,收敛速度大大提高。实验结果表明了该方法的有效性及其对噪声的较强鲁棒性。

关键词: 模糊C均值, 势函数, 最近邻算法, 图像分割

Abstract: A novel spatial potential function weighted FCM algorithm for image segmentation is presented. The algorithm is formulated by incorporating the spatial neighborhood potential function information into the original FCM clustering algorithm. The weight plays a key role in this algorithm, which is based on the principle of k-nearest neighbor (k-NN) algorithm and is extended to the neighboring pixels. The algorithm is initialized by a statistical histogram based FCM algorithm, which can speed up the convergence of the algorithm. Experimental results show the proposed algorithm is effective and more robust to noise and other artifacts than the conventional FCM algorithm.

Key words: fuzzy c-means, potential function, k-nearest neighbor algorithm, image segmentation

中图分类号: