计算机工程与应用 ›› 2007, Vol. 43 ›› Issue (24): 203-204.

• 工程与应用 • 上一篇    下一篇

基于改进型模糊聚类算法的植物病斑检测

冯登超1,2,杨兆选1,乔晓军2   

  1. 1.天津大学 电信学院,天津 300072
    2.国家农业信息化工程技术研究中心,北京 100089
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-08-21 发布日期:2007-08-21
  • 通讯作者: 冯登超

Study on detection algorithm of plant disease spot based on improved fuzzy clustering algorithm

FENG Deng-chao1,2,Yang Zhao-xuan1,QIAO Xiao-jun2   

  1. 1.School of Electronic & Information Engineering,Tianjin University,Tianjin 300072,China
    2.National Engineering Research Center for Information Technology in Agriculture,Beijing 100089,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-08-21 Published:2007-08-21
  • Contact: FENG Deng-chao

摘要: 针对植物病害图像成分复杂 、病斑排列无规则等特点,提出了一种改进型模糊聚类的病斑检测算法。该算法采用Markov随机场与模糊聚类算法耦合策略,能够有效解决植物病斑检测时的模糊性和随机性问题。仿真实验表明,改进后的算法能够实现植物病斑的自适应检测,鲁棒性较好。然而,对于Markov与模糊聚类算法的最佳耦合方式及对于如何减少算法的运算量仍需作深入的研究。

关键词: 植物病斑, 模糊C均值聚类, Markov随机场, 隶属度函数

Abstract: According to the characteristics of complex components of plant disease images and random alignment of disease spot,this paper introduces a new detection algorithm with improved fuzzy clustering algorithm.By adopting the coupled method of Markov random field and fuzzy clustering algorithm,this algorithm avoids the fuzziness and randomness during the plant disease detection.Simulation experiment shows that the improved algorithm has better robust and can realize the self-adaptive detection of plant disease spot.However,how to reduce the operating quantum of the method and get the optimal coupling method between Markov random field and fuzzy clustering algorithm need further research.

Key words: plant disease spot, fuzzy C-mean clustering, Markov random field, membership function