基于EM和K-means混合聚类方法的植物叶片病害区域自动提取

doi:10.3969/j.issn.1004-1524.2017.08.21

浙江农业学报 ›› 2017, Vol. 29 ›› Issue (8): 1384-1391.DOI: 10.3969/j.issn.1004-1524.2017.08.21

基于EM和K-means混合聚类方法的植物叶片病害区域自动提取

夏永泉, 王兵^*, 支俊, 黄海鹏, 孙静茹

郑州轻工业学院计算机与通信工程学院,河南郑州 450001

收稿日期:2017-02-28 出版日期:2017-08-20 发布日期:2017-09-06
通讯作者: 王兵,E-mail: 417726753@qq.com
作者简介:夏永泉(1972-),男,辽宁绥中人,博士,副教授,主要从事图像处理、计算机视觉、模式识别与人工智能研究。E-mail: 563241627@qq.com
基金资助:
国家自然科学基金(61302118,81501547)

Automatic extraction of plant diseases based on EM and K-means hybrid clustering

XIA Yongquan, WANG Bing^*, ZHI Jun, HUANG Haipeng, SUN Jingru

College of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450001, China

Received:2017-02-28 Online:2017-08-20 Published:2017-09-06

摘要/Abstract

摘要： 针对植物病害区域如何准确提取的问题,文中提出了一种基于EM和K-means混合聚类的方法。该方法在目标与背景具有较明显差异的情况下,可以有效地将叶片目标提取出来,并对较复杂背景也具有一定的甄别效果,优于其他经典方法。利用植物病害区域的褪绿特点,用K-means方法结合Lab颜色空间,利用Lab颜色空间颜色分布的均匀性,提取A分量作为参考分量,将病害区域从叶片目标中提取出来。通过Matlab仿真实验,结果表明,基于EM和K-means混合聚类方法的植物病害区域提取是可行的。

关键词: 植物病害区域, EM算法, Lab颜色空间, K-means算法, 混合聚类

Abstract: Aiming at the problem of how to extract the plant disease area accurately, a method based on EM and K-means hybrid clustering is proposed. The method can effectively extract the leaf target and have some screening effect on the more complicated background, which is superior to other classical methods in the case of obvious difference between the target and the background. Based on the chlorotic characteristics of the plant disease area, the K-means method was used to combine the Lab color space. Using the uniformity of the color distribution of the Lab color space, the A component was extracted as the reference component, and the disease area was extracted from the leaf target. The experimental results showed that the extraction of plant diseases based on EM and K-means hybrid clustering method is feasible.

Key words: plant disease area, EM algorithm, Lab color space, K-means algorithm, hybrid clustering

中图分类号:

TP391.41

夏永泉, 王兵, 支俊, 黄海鹏, 孙静茹. 基于EM和K-means混合聚类方法的植物叶片病害区域自动提取[J]. 浙江农业学报, 2017, 29(8): 1384-1391.

XIA Yongquan, WANG Bing, ZHI Jun, HUANG Haipeng, SUN Jingru. Automatic extraction of plant diseases based on EM and K-means hybrid clustering[J]. , 2017, 29(8): 1384-1391.

参考文献

[1] 胡维炜,张武,刘连忠,等. 利用图像处理技术计算大豆叶片相对病斑面积[J]. 江苏农业学报,2016,32(4):774-779.
HU W W,ZHANG W,LIU L Z,et al. Measurement of relative lesion area on soybean leaf using image processing technology [J]. Jiangsu Journal of Agricultural Sciences , 2016, 32(4):774-779. (in Chinese with English abstract)
[2] 李冠林,马占鸿,黄冲,等. 基于K-means硬聚类算法的葡萄病害彩色图像分割方法[J]. 农业工程学报, 2010, 26(增刊2):32-37.
LI G L, MA Z H, HUANG C, et al. Segmentation of color images of grape diseases using K-means clustering algorithm[J]. Transactions of the CSAE , 2010, 26(S2): 32-37. (in Chinese with English abstract)
[3] 张武,黄帅,汪京京,等. 复杂背景下小麦叶部病害图像分割方法研究[J]. 计算机工程与科学,2015,37(7) : 1349-1354.
ZHANG W, HUANG S, WANG J J, et al. A segmentation method for wheat leaf images with disease in complex background[J]. Computer Engineering & Science , 2015,37(7): 1349-1354. (in Chinese with English abstract)
[4] 邹秋霞,杨林楠,彭琳,等. 基于Lab空间和K-means聚类的叶片分割算法研究[J]. 农机化研究,2015(9):222-226.
ZOU Q X, YANG L N, PENG L, et al. Research on blade segmentation algorithm based on Lad space and K-means clustering[J]. Journal of Agricultural Mechanization Research , 2015(9): 222-226. (in Chinese)
[5] 谢从华, 王立军,常晋义. 面向叶子图像的植物归类的特征序列描述方法[J]. 计算机应用研究,2012,29(12): 4740-4746.
XIE C H, WANG L J, CHANG J Y. Method of signatures description of leaves images for plant categorization[J]. Application Research of Computers , 2012, 29(12): 4740-4746. (in Chinese with English abstract)
[6] 郭晶晶,李庆武,程海粟,等. 基于Lab颜色距离和GMM的树木图像分割算法[J]. 信息技术, 2016(2): 1-9.
GUO J J, LI Q W, CHENG H L, et al. Segmentation algorithm of tree image based on lab color-distance and GMM[J]. Information Technology , 2016(2): 1-9. (in Chinese with English abstract)
[7] 胡庆辉,丁立新,陆玉靖,等. 一种快速、鲁棒的有限高斯混合模型聚类算法[J]. 计算机科学,2013,40(8):191-195.
HU Q X, DING L X, LU Y J, et al. Rapid robust clustering algorithm for Gaussian finite mixture model[J]. Computer Science , 2013, 40(8): 191-195. (in Chinese with English abstract)
[8] BILIMES J A. A gentle tutorial of the EM algorithm and its application to parameter cstimation for Gaussian mixture and hidden Markov models[EB/OL]. (1998-03-25). http://ssli.cc.washington.edu/ people/bilmes/mypapers/cm.ps.gz.
[9] 庞晓敏,闵子建,阚江明. 基于HSI和LAB颜色空间的彩色图像分割[J]. 广西大学学报(自然科学版),2011, 36(6): 976-980.
PANG X M, MIN Z J, KAN J M. Color image segmentation based on HSI and LAB color space[J]. Journal of Guangxi University ( Natural Science Edition ), 2011, 36(6): 976-980. (in Chinese with English abstract)
[10] 李丽君. 结合空间信息的模糊C均值聚类的图像分割算法[J]. 辽宁石油化工大学学报,2010,30(4): 51-53.
LI L J. Fuzzy C-Means clustering algorithm with spatial information for image segmentation[J]. Journal of Liaoning Shihua University , 2010, 30(4): 51-53. (in Chinese with English abstract)
[11] 闫春来. 彩色图像分割算法的研究[D]. 成都:电子科技大学,2008: 10-11.
YAN C L. Research on color image segmentation algorithm[D]. Chengdu: University of Electronic Science and Technology, 2008: 10-11. (in Chinese with English abstract)
[12] 杨新. 图像偏微分方程的原理与应用[M]. 上海:上海交通大学出版社,2003.
[13] 刘晋浩,朱於军,阚江明. 图像分割在废弃木质材料连接件检测中的应用[J]. 广西大学学报(自然科学版), 2010, 35(6): 962-966.
LIU J H, ZHU Y J, KAN J M. The application of image processing for the segmentation of measured image of waste wood-based materials connector[J]. Journal of Guangxi University ( Natural Science Edition ), 2010, 35(6): 962-966. (in Chinese with English abstract)
[14] CHEN T W, CHEN Y L, CHEN S Y. Fast image segmentation based on K-means clustering with histograms in HSI color space[C] // IEEE 10th Workshop on Mutimedia Signal Processing(MMSP08). Queensland, Australia: Carins, 2008: 322-325.
[15] 张强,王正林. 精通MATLAB图像处理[M]. 北京:电子工业出版社, 2008: 272-279.
[16] 李中健,杜娟,郭璐. 将Otsu用于多阈值彩色图像分割的方法及优化[J]. 计算机工程与应用,2010, 46(11): 176-178.
LI Z J, DU J, GUO L. Multi-threshold segmentation and optimization based on Otsu in color image[J]. Computer Engineering and Application , 2010, 46(11): 172-178. (in Chinese with English abstract)

基于EM和K-means混合聚类方法的植物叶片病害区域自动提取

Automatic extraction of plant diseases based on EM and K-means hybrid clustering

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价