基于模板匹配的多目标水稻灯诱害虫识别方法的研究

吕军1 ,姚青1,刘庆杰1,薛杰1,陈宏明3,杨保军2,唐健2，*

doi:10.3969/j.issn.10017216.2012.05.016

中国水稻科学 >

2012 , Vol. 26 >Issue 5: 619 - 623

DOI: https://doi.org/10.3969/j.issn.10017216.2012.05.016

研究简报

基于模板匹配的多目标水稻灯诱害虫识别方法的研究

展开

¹浙江理工大学信息电子学院，浙江杭州 310018；² 中国水稻研究所，浙江杭州 310006；³象山县植保植检站，浙江象山 315700；

收稿日期: 2011-11-16

修回日期: 2012-05-16

网络出版日期: 2012-09-10

基金资助

国家自然科学基金资助项目（31071678）；浙江省重大科技项目（2010C12026）；中央级公益性科研院所基本科研业务费专项资金资助项目（2009RG0042）；宁波市科技项目（2010C10044）；浙江理工大学研究生创新基金资助项目（YCXS11022）。

收起

Identification of Multiobjective Rice Lighttrap Pests Based on Template Matching

Expand

¹ College of Informatics and Electronics, Zhejiang SciTech University, Hangzhou 310018, China; ² China National Rice Research Institute, Hangzhou 310006, China; ³ Xiangshan County Plant Protection and Quarantine Station, Xiangshan 315700, China;

Received date: 2011-11-16

Revised date: 2012-05-16

Online published: 2012-09-10

Fold

摘要

水稻灯诱害虫的识别与计数在水稻田间害虫监测中是非常重要的。由于水稻害虫被黑光灯诱集后姿态各异，存在虫体残缺现象，增加了图像自动识别的难度。在获取水稻灯诱害虫非粘连图像基础上，利用模板匹配和K折交叉验证方法进行多目标水稻灯诱害虫的识别。首先，提取每个水稻害虫图像中包括颜色、形态和纹理共156个特征参数；然后，利用主成分分析法进行数据降维，选取前6个主成分作为害虫特征参数；最后，根据每种灯诱害虫的姿态确定模板数，通过模糊C均值获得聚类中心作为模板参数，分别利用单模板和多模板匹配方法进行水稻害虫的识别。结果表明，针对姿态各异且有虫体残缺的多目标水稻灯诱害虫，多模板和单模板匹配法的识别率分别为83.1%和59.9%。

关键词： 水稻灯诱害虫; 害虫识别; 图像处理; 特征提取; 模板匹配

本文引用格式

吕军1 ,姚青1,刘庆杰1,薛杰1,陈宏明3,杨保军2,唐健2，* . 基于模板匹配的多目标水稻灯诱害虫识别方法的研究[J]. 中国水稻科学, 2012 , 26(5) : 619 -623 . DOI: 10.3969/j.issn.10017216.2012.05.016

Abstract

Identification and count of rice lighttrap pests are very important in monitoring rice pests. The pests trapped by black light lamps show different postures and incomplete bodies, which increase the difficulty of image automatic identification. Template matching and Kfold cross validation methods were used to identify multiobjective rice lighttrap pests based on nontouching pest images. Firstly, one hundred and fiftysix features including color, shape and texture features were extracted from each pest image. Secondly, the principal component analysis was employed for reducing data dimensionality, and first six principal components were selected as pests’ features. Then, the template number was determined according to the gesture of each pest species and the template parameters were obtained from the cluster centers by fuzzy Cmean clustering method. Finally, single and multitemplate matching methods were used to identify rice pests. The results showed that the accurate rate of multitemplate matching and single template matching were 83.1% and 59.9%, respectively for rice lighttrap pests with multiple postures and some incomplete bodies.

Key words： rice lighttrap pest; pest identification; image processing; feature extraction; template matching

参考文献

\[1\]张法全. 基于机器视觉和小波分析的农田害虫识别系统. 郑州: 郑州大学, 2003.

\[2\]Neethirajan S, Jayas D S, White N D G. Detection of sprouted wheat kernels using soft Xray image analysis. J Food Engin, 2007, 81: 509513.

\[3\]方明, 周龙. 基于BP神经网络的储粮害虫分类识别研究. 武汉工业学院学报, 2009, 28(4): 7073.

\[4\]Wen C, Guyer D E, Li W. Local featurebased identification and classification for orchard insects. Biosyst Engin, 2009, 104: 299307.

\[5\]Cho J, Choi J, Qiao M, et al. Automatic identification of whiteflies, aphids and thrips in greenhouse based on image analysis. Intern J Mathem Comput Simul, 2007, 4653.

\[6\]蔡清, 何东健. 基于图像分析的蔬菜食叶害虫识别技术. 计算机应用, 2010, 30(7): 18701872.

\[7\]Shariff A R M, Aik Y Y, Hong W T, et al. Automated identification and counting of pests in the paddy field using image analysis//Comput Agric Natur Resour. 4th Word Congress Conference, 2006： 759764.

\[8\]Li Z G, Fu Z T, Yan S, et al. Prototype system of automatic identification cotton insect pests and intelligent decision based on machine vision. Soc Agric Biol Engin, 2007.

\[9\]张红涛, 胡玉霞, 赵明茜, 等. 田间害虫图像识别中的特征提取与分类器设计研究. 河南农业科学, 2008（9）: 7375.

\[10\]王正宏, 宋哲存. 基于分形理论的林业害虫图像的边缘检测. 机电产品开发与创新, 2009, 22(6): 153155.

\[11\]周秀明. 基于图像识别的森林害虫分类方法研究. 哈尔滨: 东北林业大学, 2007.

\[12\]王剑, 周国民. 神经网络的水稻三化螟识别系统的研究. 农业网络信息, 2006（2）: 3942.

\[13\]Singh C B, Jayas D S, Paliwal J, et al. Identification of insectdamaged wheat kernels using shortwave nearinfrared hyperspectral and digital colour imaging. Comp Electics Agric, 2010, 73: 118125.

\[14\]Larios N, Soran B, Shapiro L G, et al. Haar random forest features and SVM spatial matching kernel for stonefly species identification. 20th International Conference on Pattern Recognition， 2010: 26242627.

\[15\]甄彤, 范艳峰. 基于支持向量机的储粮害虫分类识别技术研究. 计算机工程, 2006, 32(9): 167169.

\[16\]赵晶莹, 郭海, 孙兴滨. 基于小波分析及改进KNN的红虫识别研究. 安徽农业科学, 2009, 37(29): 1419114193.

\[17\]姚青, 吕军, 杨保军, 等. 基于图像的昆虫自动识别与计数研究进展. 中国农业科学, 2011, 44(14): 28862899.

\[18\]张孝远. 基于图像识别的农田害虫分类识别研究. 郑州: 华北水利水电学院, 2007.

\[19\]徐果毅. 基于颜色特征的图像检索研究. 长沙: 湖南大学, 2009.

\[20\]Travis D. Effective Color Displays// Theory and Practice. London: Academic Press, 1991.

\[21\]田玉敏, 林高全. 基于颜色特征的彩色图像检索方法. 西安电子科技大学学报, 2002, 29(1): 4346.

\[22\]管泽鑫, 唐健, 杨保军, 等. 基于图像的水稻病害识别方法研究. 中国水稻科学, 2010, 24(5): 497502.

\[23\]Hu M K. Visual pattern recognition by moment invariants. Inform Theory, IRE Transac, 1962, 8(2): 179182.

\[24\]赵三琴, 丁为民, 刘德营. 基于傅里叶描述子的稻飞虱形状识别. 农业机械学报, 2009, 40(8): 181184.

\[25\]章毓晋. 基于内容的视觉信息检索. 北京: 科学出版社, 2003.

\[26\]Haralick R M, Shanmugam K, Dinstein I. Textural features for image classification. IEEE Trans Syst Man Cybernet, 1973, 3(6): 610621.

\[27\]谢中华. Matlab统计分析与应用: 40个案例分析. 北京: 北京航空航天大学出版社, 2010: 354373.

\[28\]Devijver P A, Kittler J. Pattern Recognition: A Statistical Approach. London： PrenticeHall, 1982.

\[29\]Nock R, Nielsen F. On Weighting Clustering. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2006, 28(8): 113.

\[30\]李玉榕, 项国波. 一种基于马氏距离的线性判别分析分类算法. 计算机仿真, 2006, 23(8): 8688.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献