计算机工程与应用 ›› 2017, Vol. 53 ›› Issue (24): 8-14.DOI: 10.3778/j.issn.1002-8331.1710-0055

• 热点与综述 • 上一篇    下一篇

基于多链量子蜂群算法的模糊聚类图像分割

冯玉芳,卢厚清,殷  宏   

  1. 解放军陆军工程大学,南京 210007
  • 出版日期:2017-12-15 发布日期:2018-01-09

Fuzzy C-means clustering image segmentation method based on multi-chain quantum bee colony algorithm

FENG Yufang, LU Houqing, YIN Hong   

  1. PLA Army Engineering University, Nanjing 210007, China
  • Online:2017-12-15 Published:2018-01-09

摘要: 针对传统模糊C-均值聚类算法对初始值和噪声敏感的缺点,提出了一种基于多链量子蜂群算法的模糊C-均值聚类算法。首先,将多链拓展编码方案应用到量子蜂群算法中,提出了多链量子蜂群算法;其次,利用多链量子蜂群算法来优化模糊C-均值聚类的初始聚类中心;最后,设计一种新的利用多链量子蜂群算法优化模糊C-均值聚类中心的图像分割算法。实验结果表明,所提出的基于多链量子蜂群算法的模糊C-均值聚类图像分割算法是有效的,相对于传统模糊C-均值聚类算法及基于模糊的人工蜂群算法,所提算法在分割正确率、分割速度及鲁棒性上均更有效。

关键词: 图像分割, 模糊C-均值聚类, 多链拓展编码, 人工蜂群算法

Abstract: In order to solve the defects of the conventional Fuzzy C-Means(FCM) clustering algorithm which is sensitive to the selection of initial values and noise data, this paper proposes an algorithm of Fuzzy C-Means clustering based on Multi-chain Quantum Bee Colony algorithm(MQBC-FCM), Firstly, it introduces the expanded multi-chains coding method to the Quantum Artificial Bee Colony(QBC) algorithm and proposes the MQBC algorithm. Then it applies the MQBC algorithm to search for the optimal initial clustering centers. In the end, it designs a new image segmentation method based on multi-chain quantum bee colony algorithm optimizing fuzzy C-means clustering centers. The experimental results show that MQBC-FCM is efficient and the proposed method performs better in segmentation accuracy, time complexity and robustness than the image segmentation algorithms of FCM and fuzzy-based ABC.

Key words: image segmentation, fuzzy C-means clustering, expansion of multi-chain coding, artificial bee colony algorithm